© 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. 107624
    Prev
    Next
    INDEX
    Explanations

    references to secrets or secretive concepts

    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
     vloer
    -0.55
     pliers
    -0.55
     Cly
    -0.54
     Boyz
    -0.54
     workstations
    -0.53
    aughn
    -0.53
     Bryson
    -0.52
     Ply
    -0.52
     Bulls
    -0.52
     Pferd
    -0.52
    POSITIVE LOGITS
    Secret
    1.17
     secret
    1.16
     Secret
    1.16
     SECRET
    1.13
    secret
    1.11
     secrets
    1.01
    SECRET
    0.94
     Secrets
    0.93
    Secrets
    0.87
     secreto
    0.85
    Activations Density 0.006%

    No Known Activations