© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 81173
    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
     inse
    -0.52
    Tikang
    -0.48
    rmtree
    -0.48
    FunctionFlags
    -0.48
    tanleria
    -0.47
    GTCX
    -0.47
    ⁽
    -0.46
     Gim
    -0.46
    Hilfe
    -0.45
    __(/*!
    -0.44
    POSITIVE LOGITS
    XmlRootElement
    5.06
    XmlElement
    0.72
    XmlAccessorType
    0.71
     ProtoMessage
    0.62
    XmlType
    0.57
    ManagedBean
    0.57
    VersionUID
    0.54
    WebMethod
    0.54
     AssemblyCulture
    0.51
     AssemblyTitle
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.