© 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. 16-GEMMASCOPE-RES-16K
    11. 5318
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions or consequences

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

    Punctuation followed by reporting verbs

    np_acts-logits-general · gemini-2.0-flash

    reporting attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     لينك
    -0.63
    )++;
    -0.57
     Infatti
    -0.48
     gradova
    -0.48
    arParams
    -0.48
    QSize
    -0.48
    ControllerAdvice
    -0.48
    PathParam
    -0.46
    anei
    -0.45
    CPtr
    -0.45
    POSITIVE LOGITS
     reports
    1.10
     Reports
    0.95
    reports
    0.93
     reported
    0.92
    Reports
    0.89
     REPORTS
    0.89
     Reported
    0.83
    reported
    0.82
     передает
    0.81
     according
    0.81
    Activations Density 0.145%

    No Known Activations