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. 801
    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
     Italijanski
    -0.72
     Мексичка
    -0.65
     Италијани
    -0.59
    تقاوى
    -0.57
     Савезне
    -0.57
     المعيارى
    -0.57
    Personendaten
    -0.56
    webElementXpaths
    -0.56
    Jeografia
    -0.56
    MigrationBuilder
    -0.55
    POSITIVE LOGITS
    ’
    0.39
     defaultstate
    0.38
     مشين
    0.36
    isor
    0.36
    mathrm
    0.35
    }}}{\
    0.35
     miserable
    0.34
    pres
    0.34
    '
    0.34
    \}\
    0.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.