© 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. 105808
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "use" and its variants in context

    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
     contextLoads
    -0.60
    seamnă
    -0.54
    Numerade
    -0.53
     Monfieur
    -0.51
     Photocase
    -0.50
     виправивши
    -0.49
     itſelf
    -0.47
    getMenuInflater
    -0.47
    idł
    -0.47
     deſt
    -0.46
    POSITIVE LOGITS
    ThroughAttribute
    0.55
    endphp
    0.42
     future
    0.40
    thâu
    0.40
    ต่อไป
    0.39
     futuros
    0.37
    nextProps
    0.35
     inform
    0.35
     kommende
    0.34
     pod
    0.34
    Activations Density 0.049%

    No Known Activations