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. 18-GEMMASCOPE-RES-16K
    6. 14285
    Prev
    Next
    INDEX
    Explanations

    declarations of public methods in a coding context

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

    Code-related tokens like "id", "float", "override" and "protected"

    np_acts-logits-general · gemini-2.0-flash

    code structure keywords like override float

    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
    LookAnd
    -0.50
     Ades
    -0.46
     transferência
    -0.45
    green
    -0.45
    –
    -0.45
    ↵↵
    -0.45
     Green
    -0.43
     ,
    -0.43
     PLWABN
    -0.43
     _
    -0.42
    POSITIVE LOGITS
     Wicidata
    0.71
     صوتيه
    0.70
    اقرأ
    0.68
    protected
    0.68
    Hochspringen
    0.67
     protected
    0.66
     <>",
    0.65
     doInBackground
    0.63
     EnglishChoose
    0.63
     Anſ
    0.62
    Activations Density 0.019%

    No Known Activations