© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 11384
    Prev
    Next
    INDEX
    Explanations

    phrases expressing knowledge, uncertainty, or questioning of common beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    colloquial discourse lead-ins and modal/auxiliary constructions that signal questions, hedging, or conversational stance (e.g., informal second-person address and rhetorical phrasing).

    oai_token-act-pair · gpt-5Triggered by @areeb0102

    phrases that indicate thinking, wondering, believing, or expressing uncertainty.

    oai_token-act-pair · deepseek-r1Triggered by @areeb0102

    conversational discourse markers and colloquial speech patterns.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.69
     بتاريخ
    -0.64
     سكانية
    -0.61
    brengen
    -0.58
    SourceChecksum
    -0.54
     المعرف
    -0.54
     RemoteException
    -0.53
    ConfigureAwait
    -0.52
     JsonResponse
    -0.52
    tól
    -0.52
    POSITIVE LOGITS
    matchCondition
    0.82
     Савезне
    0.56
     surla
    0.56
    IndentedString
    0.56
     irony
    0.53
     الحره
    0.53
     Infórmanos
    0.52
     vou
    0.51
    pushFollow
    0.50
    MessageState
    0.50
    Activations Density 0.581%

    No Known Activations