© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10862
    Prev
    Next
    INDEX
    Explanations

    references to secrecy and secret organizations

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

    "secret" or its variations

    np_acts-logits-general · gemini-2.0-flash

    secret concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.75
    DeleteBehavior
    -0.73
    verwijspagina
    -0.72
     مرئيه
    -0.66
    fillType
    -0.65
    SerializedSize
    -0.65
    uinal
    -0.63
    MigrationBuilder
    -0.62
    NameInMap
    -0.61
    іга
    -0.60
    POSITIVE LOGITS
     Sec
    0.82
     SECRET
    0.74
     SEC
    0.70
     Secret
    0.67
    Sec
    0.67
     sec
    0.64
    SECUR
    0.63
    Secret
    0.60
     Secre
    0.60
    espace
    0.58
    Activations Density 0.161%

    No Known Activations