© 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. 6256
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations within the text

    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
    Ver
    -0.47
     للاسماء
    -0.47
    Stor
    -0.44
    jem
    -0.43
    од
    -0.42
    pogon
    -0.42
     Baz
    -0.42
    のア
    -0.42
     rodillas
    -0.42
     フィ
    -0.42
    POSITIVE LOGITS
    ImageContext
    0.98
    CloseOperation
    0.94
    UrlResolution
    0.87
    glTexCoord
    0.77
     فريبيس
    0.76
     InputDecoration
    0.76
    PreInfinity
    0.73
    ConstraintMaker
    0.73
     ?>/
    0.70
    glDelete
    0.70
    Activations Density 1.125%

    No Known Activations