© 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. 38-GEMMASCOPE-RES-16K
    11. 15285
    Prev
    Next
    INDEX
    Explanations

    issues or concerns regarding performances and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pexpr
    -0.34
     useState
    -0.34
     Familienname
    -0.33
    raisemb
    -0.32
    çeği
    -0.32
     Cerv
    -0.32
    hésite
    -0.31
     estabiliz
    -0.31
    ÓD
    -0.30
     phénom
    -0.30
    POSITIVE LOGITS
     spoiled
    1.32
     spoil
    1.31
     spoiling
    1.25
     spoilt
    1.23
     ruined
    1.20
     spoils
    1.20
     ruin
    1.19
     ruining
    1.12
     taint
    1.10
     tainted
    1.09
    Activations Density 0.701%

    No Known Activations