© 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. 121261
    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
    <eos>
    -0.33
    horabuena
    -0.33
     excepto
    -0.32
    .
    -0.31
    AndFlush
    -0.31
    us
    -0.31
    if
    -0.31
    d
    -0.30
     remplissage
    -0.30
     PRACTICE
    -0.30
    POSITIVE LOGITS
    WEBPACK
    5.88
     ***!
    1.23
    ftagPool
    1.15
    httphttps
    1.10
     autorytatywna
    1.09
     CreateTagHelper
    1.00
    SourceChecksum
    0.99
     EconPapers
    0.98
     оригіналу
    0.96
    bootstrapcdn
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.