© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104876
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a sufficient level or extent of something

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

    sufficient level or quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     Zusch
    -0.34
    kesan
    -0.34
     pagos
    -0.30
    계
    -0.29
     Sonn
    -0.29
    LIMIT
    -0.28
     Ambiental
    -0.28
    gaan
    -0.28
    WithError
    -0.28
     Hogg
    -0.27
    POSITIVE LOGITS
    enough
    1.33
     enough
    1.32
     Enough
    1.23
    Enough
    1.18
     Sufficient
    1.17
     ENOUGH
    1.15
     sufficient
    1.13
    Sufficient
    1.06
     fufficient
    1.05
     sufficiently
    1.02
    Activations Density 0.059%

    No Known Activations