© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14741
    Prev
    Next
    INDEX
    Explanations

    code components related to data types and function signatures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.82
    fjspx
    -0.77
    addCriterion
    -0.74
    ंदीखरीदारी
    -0.73
     kasarigan
    -0.72
    AsUp
    -0.69
     فريبيس
    -0.69
    localctx
    -0.68
    WriteAttribute
    -0.68
    contentLoaded
    -0.67
    POSITIVE LOGITS
     Blum
    0.37
    ("}");
    0.35
     stretch
    0.35
    []
    0.35
    asarray
    0.35
     ​
    0.34
     Res
    0.34
    меч
    0.33
     []
    0.33
     nu
    0.33
    Activations Density 0.386%

    No Known Activations