© 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. 31-GEMMASCOPE-RES-16K
    11. 13377
    Prev
    Next
    INDEX
    Explanations

    phrases indicating confidentiality or secrecy agreements

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

    instances of information being concealed, hidden, leaked, or prevented from public disclosure.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.59
     createState
    -0.45
    ceus
    -0.40
    ModelSerializer
    -0.40
    rrggbb
    -0.39
     zav
    -0.39
    ragamo
    -0.39
    Parameteri
    -0.38
     Skyline
    -0.38
    /*:
    -0.38
    POSITIVE LOGITS
     disclosure
    1.88
     disclosing
    1.82
     disclose
    1.82
     disclosed
    1.80
     reveal
    1.80
     revealing
    1.77
     revealed
    1.77
     divul
    1.69
     discloses
    1.67
     disclosures
    1.64
    Activations Density 0.789%

    No Known Activations