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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 5998
    Prev
    Next
    INDEX
    Explanations

    phrases related to "in case" scenarios

    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
     proprement
    -0.56
    
    -0.54
     rhestr
    -0.48
    OrBuilder
    -0.46
     voici
    -0.45
     aguja
    -0.45
    attuale
    -0.44
     operadores
    -0.44
    strijd
    -0.43
    ponses
    -0.43
    POSITIVE LOGITS
    万一
    0.74
     if
    0.66
    if
    0.59
     If
    0.54
    jalá
    0.53
    elsif
    0.52
     acaso
    0.50
    Przyp
    0.50
     IF
    0.49
     perchance
    0.49
    Activations Density 0.007%

    No Known Activations