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. 20-GEMMASCOPE-RES-16K
    6. 12696
    Prev
    Next
    INDEX
    Explanations

    legal terms and agreements related to policies and proceedings

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

    Follows "was," "report," or "be" in legal/official documents

    np_acts-logits-general · gemini-2.0-flash

    official document finalization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.63
    useState
    -0.63
    новниш
    -0.63
     transfieras
    -0.62
    참고
    -0.62
     resourceCulture
    -0.62
     виправивши
    -0.59
     useState
    -0.59
     ujednoznacz
    -0.59
    enderror
    -0.58
    POSITIVE LOGITS
     drafted
    1.30
     draft
    1.10
     issued
    1.02
     submitted
    0.98
     drafting
    0.98
     prepared
    0.97
     published
    0.96
     document
    0.93
     작성
    0.92
     Drafting
    0.89
    Activations Density 0.845%

    No Known Activations