© 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. 20-GEMMASCOPE-RES-131K
    11. 39326
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 's' and various slips of syntax patterns in the context of code or technical documentation

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

    singlet or forward primer

    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
    ThroughAttribute
    -0.76
     surla
    -0.74
     queſta
    -0.74
     informée
    -0.68
    PhysRev
    -0.67
    postIndex
    -0.67
    rrggbb
    -0.66
    
    -0.66
     indígen
    -0.65
     للاسماء
    -0.64
    POSITIVE LOGITS
    Exact
    0.37
     SOLE
    0.36
     solely
    0.36
    　
    0.34
     ACCUR
    0.34
    DeleteMapping
    0.33
     precisa
    0.32
    　　　
    0.32
     plain
    0.32
     Plain
    0.32
    Activations Density 0.001%

    No Known Activations