© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 14906
    Prev
    Next
    INDEX
    Explanations

    objects and tools related to eating or handling food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    scientific or technical descriptions — words naming methods, instruments, measurements, and specialized technical jargon.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    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
    CloseOperation
    -0.57
     MaterialApp
    -0.56
     useNavigate
    -0.56
    createServer
    -0.54
    Portail
    -0.53
     useParams
    -0.53
     trajets
    -0.52
    PageRoute
    -0.50
     DialogResult
    -0.50
    DialogResult
    -0.49
    POSITIVE LOGITS
    NOPQRST
    0.77
     <=",
    0.71
     Lightboxes
    0.62
    олові
    0.60
    (")");
    0.60
    twimg
    0.59
    aarrggbb
    0.57
    󠁣
    0.55
    ванович
    0.55
    InputTagHelper
    0.55
    Activations Density 32.670%

    No Known Activations