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. 11-GEMMASCOPE-RES-16K
    6. 5966
    Prev
    Next
    INDEX
    Explanations

    references to supplementary material and additional data files in academic articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.96
    SourceChecksum
    -0.89
    ########.
    -0.80
    TagMode
    -0.80
     @"/
    -0.79
    elemField
    -0.78
    цездатний
    -0.74
    évaluateur
    -0.74
    APORE
    -0.74
     feroit
    -0.74
    POSITIVE LOGITS
    setcounter
    0.68
    AnimationsModule
    0.67
    ScopeManager
    0.59
     esboço
    0.57
    abestanden
    0.53
     تضيفلها
    0.52
    mappedBy
    0.50
     
    0.50
    <eos>
    0.49
     iconFacebook
    0.47
    Activations Density 1.176%

    No Known Activations