© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3336
    Prev
    Next
    INDEX
    Explanations

    code snippets related to function definitions and return statements in programming

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

    Code-related tokens (*, if, ngx) or special symbols

    np_acts-logits-general · gemini-2.0-flash

    code comments and code structures

    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
     Ringer
    -0.63
     ErrInvalid
    -0.61
     functools
    -0.60
     Inferior
    -0.60
     Platon
    -0.59
    webf
    -0.59
     AssemblyCompany
    -0.58
     onPostExecute
    -0.58
     Joc
    -0.58
     HttpServlet
    -0.57
    POSITIVE LOGITS
    *
    0.66
    switch
    0.60
    ⓧ
    0.57
     ostavi
    0.52
    memcpy
    0.50
    if
    0.49
     *
    0.48
    *(
    0.47
    _));
    0.46
    /*
    0.45
    Activations Density 0.135%

    No Known Activations