Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8138
    Prev
    Next
    INDEX
    Explanations

    closing curly braces and the start of blocks in code

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

    Code snippets and namespaces

    np_acts-logits-general · gemini-2.0-flash

    a plurality or creature->

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.57
    Linki
    -0.55
    uxxxx
    -0.54
     متحده
    -0.53
    writeFile
    -0.52
    脚注の使い方
    -0.52
     للمعارف
    -0.52
    VideoCapture
    -0.47
    SerializedSize
    -0.47
    السكان
    -0.45
    POSITIVE LOGITS
    __;
    0.67
    MENAFN
    0.62
    andReturn
    0.57
    ThroughAttribute
    0.57
    曖昧さ回避
    0.54
    AnimationsModule
    0.54
    randomUUID
    0.53
     endregion
    0.52
    stays
    0.52
    endpush
    0.52
    Activations Density 0.113%

    No Known Activations