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. 20-GEMMASCOPE-RES-131K
    6. 90114
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     spell
    -0.33
     pronto
    -0.30
     inf
    -0.28
    life
    -0.27
    `
    -0.27
     cis
    -0.26
    ]='
    -0.26
     Spell
    -0.26
     لد
    -0.25
     vPvB
    -0.25
    POSITIVE LOGITS
    AnchorStyles
    6.69
    DockStyle
    1.37
    ValueStyle
    0.92
    addContainerGap
    0.85
     فريبيس
    0.83
    MLLoader
    0.77
     AssemblyCompany
    0.77
    EndContext
    0.75
    enumii
    0.74
    OGND
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.