© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15951
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    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
     læng
    -0.63
     plads
    -0.56
     hjælp
    -0.54
     montanha
    -0.53
    dollis
    -0.52
     provecho
    -0.52
    foque
    -0.49
     gemens
    -0.48
     netts
    -0.48
     vegetación
    -0.48
    POSITIVE LOGITS
     I
    1.28
    I
    1.21
    pI
    0.75
     i
    0.75
    iI
    0.73
    PI
    0.72
    i
    0.70
    I
    0.70
    We
    0.68
    YI
    0.68
    Activations Density 0.300%

    No Known Activations