© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 24587
    Prev
    Next
    INDEX
    Explanations

    declarations and usage of functions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code structure and function signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.69
     Infórmanos
    -0.65
    MLLoader
    -0.64
    EnableWeb
    -0.62
    ParallelGroup
    -0.61
    Tembelea
    -0.59
    ंदीखरीदारी
    -0.58
    
    -0.57
    hyrchwyd
    -0.56
     bilinear
    -0.55
    POSITIVE LOGITS
    VersionUID
    0.33
     Wund
    0.33
     void
    0.28
    complexContent
    0.26
     ujednoznacz
    0.26
    Referències
    0.26
    RetentionPolicy
    0.25
    迫
    0.25
    AssignableFrom
    0.24
    UnknownFieldSet
    0.24
    Activations Density 0.001%

    No Known Activations