© 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. 2232
    Prev
    Next
    INDEX
    Explanations

    specific syntactic structures, particularly brackets and braces

    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
    criture
    -0.43
    .
    -0.42
     Go
    -0.42
     te
    -0.41
    ’
    -0.40
    Ecotoxicity
    -0.39
    defn
    -0.39
    literals
    -0.38
    contentLoaded
    -0.38
     dagli
    -0.38
    POSITIVE LOGITS
    httphttps
    0.84
    fjspx
    0.77
    AnchorStyles
    0.77
     CGRectMake
    0.75
     hdi
    0.71
     Wickham
    0.71
     JpaRepository
    0.69
    XmlAccessType
    0.69
     intptr
    0.69
     Inks
    0.69
    Activations Density 0.060%

    No Known Activations