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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 6821
    Prev
    Next
    INDEX
    Explanations

    occurrences of phrases that introduce conditions or assumptions in mathematical contexts

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

    starts mathematical definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )•
    -0.33
     ogen
    -0.33
    Eksteraj
    -0.32
    TextHelper
    -0.32
    sendLogPayload
    -0.30
    °•
    -0.30
    /~
    -0.28
     Volkes
    -0.28
     ari
    -0.27
    /+
    -0.27
    POSITIVE LOGITS
     kasarigan
    0.67
    adaptiveStyles
    0.61
    httphttps
    0.60
    majánló
    0.59
    
    0.58
     intptr
    0.57
     Taktlose
    0.57
     Signalez
    0.57
     كومونز
    0.56
    期刊论文
    0.56
    Activations Density 0.381%

    No Known Activations