© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15900
    Prev
    Next
    INDEX
    Explanations

    references to academic journal articles and publication information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
     MainAxisSize
    -0.65
    rungsseite
    -0.63
    GIVEREF
    -0.50
    Bissau
    -0.49
     nahilalakip
    -0.46
    tableFuture
    -0.44
    pyplot
    -0.44
     referrerpolicy
    -0.43
     saites
    -0.43
    ArgumentParser
    -0.42
    POSITIVE LOGITS
    HasColumnType
    0.45
     formative
    0.42
     bezpiecze
    0.41
    StructEnd
    0.39
    conversion
    0.36
     Auff
    0.34
     rembour
    0.34
    клопе
    0.33
    TextAppearance
    0.33
    เท
    0.33
    Activations Density 0.288%

    No Known Activations