© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104615
    Prev
    Next
    INDEX
    Explanations

    statistical comparisons and increases in measurements or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lycka
    -0.40
    wußt
    -0.39
    Према
    -0.36
     credit
    -0.35
     suitcase
    -0.34
     lately
    -0.34
     stric
    -0.32
     crédit
    -0.32
    hesus
    -0.32
     član
    -0.31
    POSITIVE LOGITS
     referrerpolicy
    0.56
    IsContent
    0.50
    drake
    0.50
    assertj
    0.48
     nearly
    0.47
    WriteBarrier
    0.47
    EDEFAULT
    0.45
     فريبيس
    0.44
    BooleanField
    0.43
    writeFieldEnd
    0.43
    Activations Density 0.075%

    No Known Activations