© 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. 81482
    Prev
    Next
    INDEX
    Explanations

    references to structures and environments associated with buildings and plumbing systems

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

    boundaries or outer surfaces

    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
    évaluateur
    -0.56
     мәкал
    -0.53
     resourceCulture
    -0.52
    UrlResolution
    -0.51
    sizeCache
    -0.49
    diğinde
    -0.49
     informée
    -0.48
     sendiri
    -0.47
     yyr
    -0.47
    čiai
    -0.46
    POSITIVE LOGITS
    +#+#
    0.44
    AnimationsModule
    0.44
    Diweddarwch
    0.42
    MessageState
    0.40
    plish
    0.37
    Xna
    0.37
     LayoutInflater
    0.37
     Waits
    0.36
     near
    0.35
     AB
    0.35
    Activations Density 0.067%

    No Known Activations