© 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. 22-GEMMASCOPE-RES-16K
    11. 6513
    Prev
    Next
    INDEX
    Explanations

    programming-related function calls and object property accesses

    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
    :✨
    -0.79
    UnusedPrivate
    -0.79
     AssemblyCompany
    -0.78
    الحياه
    -0.74
    writeFieldEnd
    -0.72
    StructEnd
    -0.70
    Tikang
    -0.69
    RenderAtEndOf
    -0.69
    featureID
    -0.69
    ьаж
    -0.63
    POSITIVE LOGITS
    led
    0.40
     trace
    0.40
     fine
    0.37
    TryGetValue
    0.35
    Trace
    0.34
     led
    0.34
     <
    0.32
     Das
    0.32
     Fine
    0.32
     Trace
    0.32
    Activations Density 0.266%

    No Known Activations