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
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 927
    Prev
    Next
    INDEX
    Explanations

    expressions of belief or doubt

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

    "believe" or its variations

    np_acts-logits-general · gemini-2.0-flash

    believe me or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kassel
    -0.52
    terdam
    -0.50
     Sjö
    -0.50
    nash
    -0.49
     Sauce
    -0.49
     Rouen
    -0.48
     Marius
    -0.47
     Toms
    -0.47
     lat
    -0.47
     quad
    -0.46
    POSITIVE LOGITS
     believe
    0.89
     Believe
    0.82
    Believe
    0.81
    believe
    0.79
     BELIEVE
    0.79
     belief
    0.76
     Belief
    0.75
     Belie
    0.73
     believes
    0.72
     дописавши
    0.70
    Activations Density 0.068%

    No Known Activations