© 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. 123612
    Prev
    Next
    INDEX
    Explanations

    mentions of specific items or entities that indicate data or types of information

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

    | studies| sponges| person

    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
    mically
    -0.31
    -
    -0.30
     Unters
    -0.30
     reca
    -0.28
     المعل
    -0.28
     lazily
    -0.27
     hayal
    -0.26
     sun
    -0.26
    cut
    -0.25
     Slowly
    -0.25
    POSITIVE LOGITS
    SourceChecksum
    0.75
    rungsseite
    0.73
     autorytatywna
    0.71
     ivelany
    0.69
    IVEREF
    0.69
     يتيمه
    0.68
     NSCoder
    0.65
     queſta
    0.65
    Tembelea
    0.65
    UserScript
    0.64
    Activations Density 0.110%

    No Known Activations