© 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. 22-GEMMASCOPE-RES-16K
    11. 13192
    Prev
    Next
    INDEX
    Explanations

    documentation comments indicating class and method descriptions or licensing information

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

    Code-related comments or documentation

    np_acts-logits-general · gemini-2.0-flash

    /**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.87
    UnusedPrivate
    -0.84
    ChildScrollView
    -0.76
    IsMutable
    -0.71
    FunctionFlags
    -0.66
     SqlParameter
    -0.66
    featureID
    -0.63
     nargin
    -0.63
    makeConstraints
    -0.61
     Administrativna
    -0.61
    POSITIVE LOGITS
     class
    0.92
     Class
    0.84
     Represents
    0.78
     Created
    0.78
     classe
    0.77
     represents
    0.76
     clase
    0.76
    Класс
    0.73
    Class
    0.71
     represent
    0.70
    Activations Density 0.199%

    No Known Activations