© 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. 7785
    Prev
    Next
    INDEX
    Explanations

    elements related to media sources or references

    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
     strip
    -0.34
     stored
    -0.34
    zens
    -0.32
     higher
    -0.31
     controlled
    -0.30
     implemented
    -0.30
     pro
    -0.30
     c
    -0.30
     learned
    -0.30
     field
    -0.29
    POSITIVE LOGITS
    featureID
    0.75
     jspb
    0.75
     HasFactory
    0.73
     autorytatywna
    0.73
     wikipagina
    0.71
     ujednoznacz
    0.69
    MigrationBuilder
    0.67
    makeConstraints
    0.66
    expandindo
    0.65
    migrationBuilder
    0.65
    Activations Density 0.612%

    No Known Activations