© 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. 1711
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ſicht
    -0.89
    AddTagHelper
    -0.89
    RuleContext
    -0.86
    mpagne
    -0.85
    ſehen
    -0.85
     '\\;'
    -0.85
    ロウィン
    -0.85
    ſſung
    -0.84
     deſſen
    -0.84
    <unused8>
    -0.84
    POSITIVE LOGITS
    .
    0.30
    ※
    0.27
    NVIC
    0.25
    <h1>
    0.24
    。
    0.23
     to
    0.22
    čius
    0.21
    def
    0.21
    //
    0.19
     Numerade
    0.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.