© 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. 31-GEMMASCOPE-RES-16K
    11. 3363
    Prev
    Next
    INDEX
    Explanations

    general instructions related to cooking or food preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    instructions and procedural steps involving heating, temperature specifications, and preparation methods.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ListTile
    -0.43
    KURZBESCHREIBUNG
    -0.42
    liquidity
    -0.38
    componentWill
    -0.37
    issory
    -0.35
     ná
    -0.34
    хьтан
    -0.34
     athe
    -0.33
    Portail
    -0.33
    virons
    -0.32
    POSITIVE LOGITS
     oven
    1.51
     Oven
    1.27
    Oven
    1.23
     bake
    1.20
     ovens
    1.19
    oven
    1.18
     baking
    1.13
     baked
    1.07
    Bake
    1.05
     horno
    1.04
    Activations Density 0.185%

    No Known Activations