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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K__L0-22
    6. 90
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.95
     AssemblyCulture
    -0.94
    awtextra
    -0.92
     EconPapers
    -0.83
    AddTagHelper
    -0.79
    ValueStyle
    -0.79
    NOPQRST
    -0.78
     StatelessWidget
    -0.76
    ]")]
    -0.74
    __':
    
    -0.73
    POSITIVE LOGITS
    Clik
    0.45
    @
    0.45
     bocas
    0.43
    ondy
    0.43
    @@
    0.43
    Famille
    0.43
     https
    0.42
    anim
    0.42
     nå
    0.42
    {'
    0.41
    Activations Density 0.082%

    No Known Activations