© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 54320
    Prev
    Next
    INDEX
    Explanations

    phrases related to deception or fabrication

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

    invent or make up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.50
    出版年
    -0.41
    indre
    -0.39
    savevideobot
    -0.39
    يميديا
    -0.38
     صفحۀ
    -0.37
    GraphicsUnit
    -0.37
    ampingi
    -0.36
    енча
    -0.36
    ьаж
    -0.36
    POSITIVE LOGITS
     invented
    0.67
     invent
    0.65
     inventing
    0.65
     Invent
    0.57
     fabricate
    0.57
    Invent
    0.55
    invent
    0.53
    makeText
    0.52
     fabricated
    0.51
     invention
    0.51
    Activations Density 0.039%

    No Known Activations