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. 84493
    Prev
    Next
    INDEX
    Explanations

    expressions of belief or conviction

    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
     Rouen
    -0.57
     UTM
    -0.57
     Ome
    -0.56
     SPS
    -0.56
     Somers
    -0.56
     Gard
    -0.55
     PTA
    -0.55
    gerton
    -0.54
     Ramos
    -0.54
    TMS
    -0.54
    POSITIVE LOGITS
     believe
    1.02
     BELIEVE
    0.93
     Believe
    0.91
    believe
    0.91
     belief
    0.90
    Believe
    0.90
     believes
    0.86
     believing
    0.81
     Belief
    0.80
     Belie
    0.79
    Activations Density 0.022%

    No Known Activations