© 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. 21-GEMMASCOPE-RES-16K
    11. 14090
    Prev
    Next
    INDEX
    Explanations

    areas related to programming syntax, particularly references to functions, methods, and attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -1.10
    ########.
    -1.05
     tartalomajánló
    -0.89
     ExecuteAsync
    -0.86
    '},
    -0.84
    {}",
    -0.84
     Roskov
    -0.83
    ]")]
    -0.83
     Италијани
    -0.82
     AssemblyTitle
    -0.82
    POSITIVE LOGITS
    //
    1.89
     //
    1.30
    <!--
    1.04
    {/*
    1.01
    ///
    0.96
    <strong>
    0.94
    #
    0.91
    /*
    0.89
    ){//
    0.87
    );//
    0.86
    Activations Density 0.136%

    No Known Activations