© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1901
    Prev
    Next
    INDEX
    Explanations

    function calls and file operations in programming code

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

    File operations (close, flush, release, trim)

    np_acts-logits-general · gemini-2.0-flash

    method calls ending in parentheses

    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
    Ārējās
    -0.91
    '):
    -0.82
    '}>
    -0.80
    ]:
    -0.75
    '],
    -0.73
     ModelExpression
    -0.72
    LookAnd
    -0.72
    ")));
    -0.71
    '){
    -0.71
    '),
    -0.71
    POSITIVE LOGITS
    ();
    0.64
    NewGuid
    0.63
    ()
    0.60
    .
    0.56
    ().
    0.51
     rând
    0.48
     étrangères
    0.48
    (),
    0.47
     Bioaccumulative
    0.45
    maketitle
    0.45
    Activations Density 0.093%

    No Known Activations