Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 772
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.59
    WriteTagHelper
    -0.44
    NamedQueries
    -0.40
    ConstraintMaker
    -0.38
    irited
    -0.37
    reactstrap
    -0.37
     bornes
    -0.36
    WebElementEntity
    -0.35
    matchCondition
    -0.35
     Administrativna
    -0.35
    POSITIVE LOGITS
    ValueStyle
    0.52
    endcsname
    0.48
    NUMX
    0.46
     userType
    0.45
    ffilm
    0.44
     
    0.44
    onOptions
    0.44
    tagHelperRunner
    0.44
     newItem
    0.44
     totalSupply
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.