Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7241
    Prev
    Next
    INDEX
    Explanations

    mentions of free offerings or resources

    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
    taciones
    -0.52
     kleding
    -0.47
    NTSTATUS
    -0.47
    ations
    -0.47
     Chapter
    -0.47
     novelas
    -0.46
    beelding
    -0.45
    onson
    -0.45
    itects
    -0.44
     fatos
    -0.44
    POSITIVE LOGITS
    Free
    1.13
     Free
    1.10
     free
    1.02
    free
    1.02
     FREE
    0.95
    FREE
    0.93
     frees
    0.79
     Freeport
    0.78
    freed
    0.76
     libre
    0.73
    Activations Density 0.170%

    No Known Activations