Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45517
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "from" related to imports in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    новниш
    -0.94
     betweenstory
    -0.83
    RegressionTest
    -0.75
     pleaſure
    -0.74
    +#+#
    -0.73
     メンテナ
    -0.69
    ꊥ
    -0.69
     InputDecoration
    -0.69
     パンチラ
    -0.69
    writeFieldEnd
    -0.68
    POSITIVE LOGITS
    from
    0.43
     from
    0.42
    CppMethod
    0.37
    ><!--
    0.35
    From
    0.34
     From
    0.33
    BeginInit
    0.29
    Thank
    0.28
     FROM
    0.28
    GOTREF
    0.28
    Activations Density 0.000%

    No Known Activations