© 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. 4-GEMMASCOPE-RES-16K
    11. 1829
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements, specifically function calls and return statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.54
    łaszcza
    -0.50
     Roskov
    -0.49
    isdir
    -0.48
    atimes
    -0.46
     rowspan
    -0.46
    BitConverter
    -0.46
    conio
    -0.44
    moveToNext
    -0.43
     voudrais
    -0.42
    POSITIVE LOGITS
     ddelweddau
    0.85
    UnusedPrivate
    0.84
    WebServlet
    0.77
    IsContent
    0.72
    fjspx
    0.68
     Signalez
    0.68
    MessageInfo
    0.68
    principalColumn
    0.67
    Rhestr
    0.67
    colhead
    0.66
    Activations Density 0.258%

    No Known Activations