© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 6195
    Prev
    Next
    INDEX
    Explanations

    references to error handling and response in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    openConnection
    -0.43
    hideLoading
    -0.34
    slidesToShow
    -0.32
    Enllaços
    -0.32
    また
    -0.30
    easy
    -0.29
    Domestic
    -0.29
    生
    -0.29
    неве
    -0.29
    owol
    -0.29
    POSITIVE LOGITS
    r
    2.56
    rs
    1.16
    rC
    1.16
    rB
    1.13
    rA
    1.12
    rse
    1.09
    rg
    1.07
    rr
    1.05
    rn
    1.04
    rch
    1.02
    Activations Density 0.409%

    No Known Activations