© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 87149
    Prev
    Next
    INDEX
    Explanations

    references to licensing and implementation details in software

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

    is followed by descriptions

    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
     ***!
    -0.61
     GenerationType
    -0.61
    PropertyChanging
    -0.59
    styleType
    -0.58
    AutoField
    -0.54
     informée
    -0.54
    bootstrapcdn
    -0.47
    SBATCH
    -0.47
    SequentialGroup
    -0.46
    __;
    -0.46
    POSITIVE LOGITS
     kuma
    0.44
     usability
    0.43
    เก
    0.42
    oléon
    0.41
    äumt
    0.41
    principle
    0.40
    ITOS
    0.40
    檔
    0.39
     expanding
    0.39
     Tä
    0.39
    Activations Density 0.124%

    No Known Activations