© 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. 19-GEMMASCOPE-RES-16K
    11. 2721
    Prev
    Next
    INDEX
    Explanations

    deeply technical or scientific terms, particularly in the context of genetics or software specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.60
    SharedCtor
    -0.47
    adaptiveStyles
    -0.47
    posedge
    -0.46
    vible
    -0.45
    createServer
    -0.43
    cytes
    -0.42
    Exceeded
    -0.42
    Articolo
    -0.42
    gnose
    -0.42
    POSITIVE LOGITS
     group
    1.29
     cluster
    1.26
     batch
    1.24
     groups
    1.20
     bunch
    1.11
     collection
    1.11
     grouping
    1.10
     clusters
    1.10
     groupe
    1.06
     pack
    1.06
    Activations Density 1.119%

    No Known Activations