© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15614
    Prev
    Next
    INDEX
    Explanations

    instances of interpersonal interactions and social dynamics, particularly those involving authority or control

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

    preceding verbs

    np_acts-logits-general · gemini-2.0-flash

    commit violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    مراجع
    -0.39
    tagHelperRunner
    -0.38
    ือก
    -0.33
     monot
    -0.32
    níků
    -0.31
    Own
    -0.31
    erade
    -0.30
    韧
    -0.29
     PAUL
    -0.29
     Gruß
    -0.29
    POSITIVE LOGITS
    IntoConstraints
    0.74
     Inſ
    0.60
    awtextra
    0.57
    CopyWith
    0.53
     Eſ
    0.52
    Становништво
    0.52
    InputBorder
    0.52
     eſſ
    0.51
     Reſ
    0.51
    Халык
    0.51
    Activations Density 0.735%

    No Known Activations