© 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. 11814
    Prev
    Next
    INDEX
    Explanations

    code snippets relating to database interactions, specifically SQL queries and operations

    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
    uberge
    -0.55
    Datuak
    -0.55
    borderSide
    -0.53
    Hozzáférés
    -0.52
    ribune
    -0.51
    INDU
    -0.51
    sique
    -0.50
     forti
    -0.50
     progresses
    -0.49
    FilterChain
    -0.48
    POSITIVE LOGITS
    >{@
    0.62
    tagext
    0.61
     ExecuteAsync
    0.60
    aneity
    0.57
    transQ
    0.54
    ')")
    0.52
     vulgaires
    0.51
    oredCriteria
    0.50
    ']")
    0.49
    memoized
    0.48
    Activations Density 0.039%

    No Known Activations