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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 101553
    Prev
    Next
    INDEX
    Explanations

    instances of the word "admit" and its variations

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

    admit to or admit that

    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-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
     Kura
    -0.49
    The
    -0.49
    Musique
    -0.48
     steampunk
    -0.48
    Simply
    -0.48
     ordnance
    -0.48
     Dyn
    -0.48
     PSO
    -0.47
     simply
    -0.47
    orderId
    -0.47
    POSITIVE LOGITS
     admit
    0.92
     admits
    0.91
     Admit
    0.90
     admitted
    0.86
     admitting
    0.84
    testify
    0.68
     admission
    0.67
     admiti
    0.65
     admite
    0.65
     admitir
    0.65
    Activations Density 0.012%

    No Known Activations