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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 45501
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs or phrases related to movement or direction

    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
    Predecesor
    -0.59
     tartalomajánló
    -0.57
     ویکی‌پدی
    -0.57
     enfans
    -0.55
    bildēt
    -0.55
     zoude
    -0.52
    actéristi
    -0.52
     surla
    -0.51
     تضيفلها
    -0.50
    ientras
    -0.49
    POSITIVE LOGITS
    躇
    0.90
     in
    0.57
    zzleHttp
    0.54
    fortawesome
    0.49
    揄
    0.48
    checkOut
    0.46
     by
    0.46
     Lawler
    0.45
     for
    0.44
    зре
    0.43
    Activations Density 0.064%

    No Known Activations