© 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. 20-GEMMASCOPE-RES-16K
    11. 13937
    Prev
    Next
    INDEX
    Explanations

    technical terms and abbreviations related to computational processes, specifically in programming and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PREFERRED
    -0.65
    IMPORTED
    -0.63
    ScopeManager
    -0.62
    มาะ
    -0.60
    ised
    -0.59
    ruptedException
    -0.59
    ation
    -0.58
     dezelve
    -0.58
    ölkerung
    -0.57
    клопе
    -0.57
    POSITIVE LOGITS
    Beijinhos
    0.60
    cartão
    0.53
     PhD
    0.52
     CS
    0.50
     MD
    0.48
    hljs
    0.47
     NW
    0.47
     ML
    0.47
    adeloupe
    0.46
    COUVER
    0.46
    Activations Density 1.107%

    No Known Activations