© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 86516
    Prev
    Next
    INDEX
    Explanations

    function calls with parentheses in the programming context

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

    ```javaGson().fromJson```

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ſtate
    -0.79
     juſ
    -0.79
     houſe
    -0.78
     quæ
    -0.77
     pleaſure
    -0.74
     ſche
    -0.71
     ſon
    -0.70
     ſtre
    -0.69
     Majefty
    -0.68
    onAttach
    -0.67
    POSITIVE LOGITS
    ().
    1.16
    ()->
    0.89
    >().
    0.81
    ()?.
    0.72
    ().__
    0.71
     ().
    0.67
    ()).
    0.65
     Cullen
    0.60
    ::
    0.57
    ()
    0.55
    Activations Density 0.009%

    No Known Activations