© 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. 15-GEMMASCOPE-RES-16K
    11. 3826
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and issues surrounding criminality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.68
    kozás
    -0.59
    országban
    -0.57
    sizeCache
    -0.54
    :
    -0.54
    .
    -0.54
     Tropfen
    -0.54
     quæ
    -0.54
     регионе
    -0.54
     eorum
    -0.53
    POSITIVE LOGITS
    RenderAtEndOf
    0.94
     مشين
    0.89
    ArgsConstructor
    0.88
    Slf
    0.84
    testens
    0.80
     TextInputType
    0.76
    TagMode
    0.74
    neous
    0.74
    存于互联网档案馆
    0.73
    ViewImports
    0.73
    Activations Density 0.931%

    No Known Activations