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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 30838
    Prev
    Next
    INDEX
    Explanations

    URL patterns and structures in text

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

    http:// addresses

    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
    GEBURTSDATUM
    -0.59
     незавершена
    -0.54
    IntoConstraints
    -0.53
     CURIAM
    -0.53
     unknownFields
    -0.52
    tangentMode
    -0.50
     Normdatei
    -0.49
     mangá
    -0.48
     ejus
    -0.48
    الحياه
    -0.47
    POSITIVE LOGITS
    
    0.39
     visit
    0.38
     address
    0.34
     Ballard
    0.34
    Cuándo
    0.33
     محل
    0.33
     visits
    0.33
     visited
    0.33
    ถ
    0.32
     Visit
    0.32
    Activations Density 0.007%

    No Known Activations