Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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
    6. 6229
    Prev
    Next
    INDEX
    Explanations

    mixed entities and numerical data associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
    UnusedPrivate
    -0.66
    ngdoc
    -0.59
    ;"></
    -0.53
     sumpay
    -0.52
    ########.
    -0.50
    #>
    -0.49
    vician
    -0.49
    */;
    -0.47
    -</
    -0.47
    pentry
    -0.47
    POSITIVE LOGITS
    UrlResolution
    0.74
     aka
    0.66
     yani
    0.66
    /
    0.63
    getActiveSheet
    0.63
     alias
    0.61
    MessageOf
    0.61
    TagMode
    0.58
     (
    0.57
     AKA
    0.57
    Activations Density 0.742%

    No Known Activations