© 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. 9-GEMMASCOPE-RES-131K
    6. 12719
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jenis
    -0.34
     blood
    -0.33
    iyle
    -0.33
     Jenis
    -0.32
     tenido
    -0.30
     bienes
    -0.30
     solchen
    -0.29
     liberar
    -0.29
     enseñanza
    -0.29
     étrangère
    -0.29
    POSITIVE LOGITS
    cshtml
    4.84
    razor
    1.22
    xaml
    1.08
    SourceChecksum
    1.02
     <<<<<<<<<<<<<<
    1.00
    ViewFeatures
    0.94
     ExecuteAsync
    0.92
    endphp
    0.89
    TagHelper
    0.85
    VersionUID
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.