© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15321
    Prev
    Next
    INDEX
    Explanations

    expressions related to various forms of belief and conviction

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

    "believe" or its variations

    np_acts-logits-general · gemini-2.0-flash

    believe that or believe in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Kassel
    -0.58
     Ome
    -0.58
     Rouen
    -0.56
     Gardiner
    -0.55
     Gard
    -0.52
     inexplicable
    -0.52
     Langford
    -0.51
    poisson
    -0.51
     Somers
    -0.51
     Omar
    -0.50
    POSITIVE LOGITS
     believe
    1.05
     belief
    1.04
     BELIEVE
    0.98
     Belief
    0.98
     Believe
    0.96
    Believe
    0.92
     believes
    0.90
    believe
    0.89
     believing
    0.85
     Belie
    0.85
    Activations Density 0.090%

    No Known Activations