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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 12774
    Prev
    Next
    INDEX
    Explanations

    references to secrets and hidden information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ddelwed
    -0.64
     ſind
    -0.63
    bibfield
    -0.60
     ſehen
    -0.60
     Spouse
    -0.59
     BorderSide
    -0.59
    UrlResolution
    -0.58
    ٞ
    -0.58
    spouse
    -0.58
     Waſſer
    -0.57
    POSITIVE LOGITS
     secret
    1.68
    Secret
    1.53
     Secret
    1.52
    secret
    1.50
     SECRET
    1.47
     secrets
    1.38
    SECRET
    1.27
     secreto
    1.25
     Secrets
    1.23
    Secrets
    1.20
    Activations Density 0.175%

    No Known Activations