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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14753
    Prev
    Next
    INDEX
    Explanations

    function definitions and error handling within the code

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

    Start of variable, type, or function declaration

    np_acts-logits-general · gemini-2.0-flash

    code declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     async
    -0.92
    async
    -0.87
    AndEndTag
    -0.62
    异步
    -0.55
    ASYNC
    -0.52
    UnifiedTopology
    -0.51
     يتيمه
    -0.51
     asynchronous
    -0.50
    UnusedPrivate
    -0.49
    OGND
    -0.49
    POSITIVE LOGITS
    func
    0.82
     func
    0.77
    Func
    0.39
    var
    0.37
     type
    0.36
    type
    0.36
     Func
    0.36
     var
    0.34
     Fun
    0.34
     Bears
    0.31
    Activations Density 0.296%

    No Known Activations