© 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. 39-GEMMASCOPE-RES-16K
    11. 4699
    Prev
    Next
    INDEX
    Explanations

    references to personal names or entities associated with contexts in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endregion
    -0.63
    jspb
    -0.60
    transQ
    -0.59
    ValueStyle
    -0.55
    はじめに
    -0.55
    ThroughAttribute
    -0.52
     يتيمه
    -0.52
     مشين
    -0.52
    enderror
    -0.51
    -------------</
    -0.50
    POSITIVE LOGITS
    su
    0.53
    ses
    0.50
    sy
    0.50
    ser
    0.47
    suri
    0.47
    sa
    0.43
    sum
    0.41
    saus
    0.40
    sk
    0.39
    said
    0.38
    Activations Density 0.275%

    No Known Activations