© 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. 3-GEMMASCOPE-RES-16K
    11. 8725
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to formal proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    -0.60
    ,
    -0.55
    :"-"`
    -0.54
    :
    -0.54
    .
    -0.53
    SourceChecksum
    -0.52
    '
    -0.51
     HasFactory
    -0.45
    ings
    -0.44
    ETHOD
    -0.43
    POSITIVE LOGITS
     nakalista
    0.53
    tvguidetime
    0.52
     faſt
    0.51
     Perſ
    0.49
    httphttps
    0.48
     itſelf
    0.47
     ſch
    0.47
     Conſ
    0.46
     himſelf
    0.45
     ReactDOM
    0.44
    Activations Density 0.609%

    No Known Activations