© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1690
    Prev
    Next
    INDEX
    Explanations

    technical explanations and processes related to programming and system operations

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

    Sentences that end with a period

    np_acts-logits-general · gemini-2.0-flash

    each subsequent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invokingState
    -0.60
    むしろ
    -0.57
     tampoco
    -0.56
     Pourtant
    -0.56
     ويكيپيديا
    -0.55
     pourtant
    -0.55
     Tampoco
    -0.55
     Infatti
    -0.53
    Hentet
    -0.52
    ьаж
    -0.52
    POSITIVE LOGITS
     Thereafter
    0.96
     thereafter
    0.92
     then
    0.87
     each
    0.84
     subsequent
    0.83
     Afterwards
    0.83
    Afterwards
    0.82
     afterwards
    0.80
     Each
    0.79
     subsequently
    0.78
    Activations Density 0.642%

    No Known Activations