© 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. 10-GEMMASCOPE-RES-16K
    11. 12487
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and types related to data structures and collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UITableViewCell
    -0.48
    SourceChecksum
    -0.47
     Bad
    -0.46
    IBOutlet
    -0.46
    uel
    -0.45
     Busy
    -0.44
    klen
    -0.40
    myModal
    -0.39
     bet
    -0.39
    LabelTagHelper
    -0.38
    POSITIVE LOGITS
     Audiodateien
    1.02
    Transkript
    0.83
     SafeMath
    0.76
    IsMutable
    0.73
    yarnpkg
    0.72
    Personensuche
    0.70
    Hochspringen
    0.69
    StructEnd
    0.68
     ModelExpression
    0.67
    abestanden
    0.66
    Activations Density 0.162%

    No Known Activations