Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 2410
    Prev
    Next
    INDEX
    Explanations

    functions related to formatting strings

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

    string formatting functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    
    -0.58
    Ӕ
    -0.53
     queſta
    -0.50
     UserDao
    -0.49
    getch
    -0.48
    webElementGuid
    -0.48
    #![
    -0.48
    ſammen
    -0.44
    inSlope
    -0.44
    rrggbb
    -0.44
    POSITIVE LOGITS
    Sprintf
    1.35
    WithFormat
    0.94
     sprintf
    0.83
    sprintf
    0.81
    Errorf
    0.63
    Fprintf
    0.61
    Format
    0.59
    format
    0.57
    Printf
    0.57
    WriteAttribute
    0.56
    Activations Density 0.006%

    No Known Activations