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. 51943
    Prev
    Next
    INDEX
    Explanations

    phrases related to prevention and consequences of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    parsedMessage
    -0.65
     समीक्षक
    -0.52
     autorytatywna
    -0.52
    ConstraintMaker
    -0.52
    jspb
    -0.51
    ніципалі
    -0.51
     utafitiHapana
    -0.49
    tiérrez
    -0.49
     Мексичка
    -0.48
    */].
    -0.48
    POSITIVE LOGITS
     occurrence
    0.42
     nahilalakip
    0.41
     Zukunft
    0.40
     occurrences
    0.40
    roffenen
    0.40
     future
    0.40
     geval
    0.39
     случай
    0.38
     behaviour
    0.38
     behavior
    0.37
    Activations Density 0.017%

    No Known Activations