© 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. 12401
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements in programming code

    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
    ฝ
    -0.67
    udad
    -0.66
    igold
    -0.63
    oot
    -0.63
    gger
    -0.63
     Wib
    -0.63
     capital
    -0.62
    rams
    -0.60
    archical
    -0.60
    peg
    -0.60
    POSITIVE LOGITS
    __":
    1.93
    __':
    1.91
    __':
    1.87
    __":
    1.86
    "])){
    1.26
    }))
    1.24
    '])){
    1.16
    ))){
    1.12
     الحره
    1.11
     }))
    1.08
    Activations Density 0.023%

    No Known Activations