© 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. 3217
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a recipe or cooking process

    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
    SourceChecksum
    -0.50
    RenderAtEndOf
    -0.48
    ContentAsync
    -0.40
    ExtendWith
    -0.39
    ContentAlignment
    -0.36
     drapeau
    -0.36
     defeat
    -0.36
     ministerial
    -0.35
    InputBorder
    -0.35
    läufig
    -0.34
    POSITIVE LOGITS
     ferment
    1.02
     fermentation
    1.01
     Fermentation
    0.86
     fermented
    0.85
     soaking
    0.78
     fer
    0.77
     aging
    0.75
     ageing
    0.71
    Fer
    0.69
     boiling
    0.69
    Activations Density 0.328%

    No Known Activations