© 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. 20-GEMMASCOPE-RES-16K
    11. 5242
    Prev
    Next
    INDEX
    Explanations

    conditional statements and expressions of potential outcomes

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

    conditional statements or hypothetical scenarios using words like "if", "then", and "could".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     contextLoads
    -0.28
     متحده
    -0.28
     instead
    -0.28
     tournage
    -0.27
     vínculo
    -0.25
     uniformly
    -0.25
     Choisissez
    -0.24
     tibur
    -0.24
     quoque
    -0.24
     tirantes
    -0.24
    POSITIVE LOGITS
    цездатний
    0.98
    참고
    0.85
    complexContent
    0.80
    ValueGenerated
    0.73
    NamedQueries
    0.73
    ագրություններ
    0.73
    oredCriteria
    0.70
    Ⴈ
    0.70
    脚注の使い方
    0.69
     PagesJaunes
    0.69
    Activations Density 1.191%

    No Known Activations