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

    Neuronpedia

    APICircuit 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. 91993
    Prev
    Next
    INDEX
    Explanations

    instances of contrast or exceptions within statements

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

    concessive clauses

    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
     and
    -0.35
     cérami
    -0.30
    就是
    -0.28
     céramique
    -0.28
     Turkey
    -0.28
     français
    -0.27
     municipalité
    -0.27
    Jeden
    -0.26
     transforma
    -0.26
     nämlich
    -0.26
    POSITIVE LOGITS
    principalColumn
    0.76
     Италијани
    0.76
    fromnode
    0.75
    exitRule
    0.73
    rungsseite
    0.71
     queſta
    0.66
    setupUi
    0.64
     zoude
    0.64
     protoimpl
    0.63
    +#+#
    0.63
    Activations Density 0.037%

    No Known Activations