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. 1153
    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
     bæ
    -0.34
    ือ
    -0.33
     maș
    -0.32
    aksikan
    -0.31
     восстанов
    -0.31
    چال
    -0.31
     repaired
    -0.30
     viață
    -0.30
     local
    -0.30
     used
    -0.29
    POSITIVE LOGITS
    nestjs
    5.00
    ngrx
    1.20
     TestBed
    1.04
    typeorm
    1.00
    ValueStyle
    0.88
     NgModule
    0.81
    BASEPATH
    0.81
    getDoctrine
    0.79
    TypedDataSet
    0.79
    zzleHttp
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.