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. 25-GEMMASCOPE-RES-16K
    6. 10424
    Prev
    Next
    INDEX
    Explanations

    specific references to sporting events or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.87
    tagHelperRunner
    -0.67
    Personendaten
    -0.67
     gärna
    -0.65
    Xna
    -0.65
    extAlignment
    -0.63
    setVerticalGroup
    -0.60
    unhofer
    -0.59
    ientôt
    -0.57
    DrawerToggle
    -0.56
    POSITIVE LOGITS
     en
    0.88
     behind
    0.82
     thanks
    0.76
     capped
    0.69
    featureID
    0.69
     highlighted
    0.66
    behind
    0.65
     capping
    0.63
    Behind
    0.60
     snapping
    0.59
    Activations Density 0.236%

    No Known Activations