© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15222
    Prev
    Next
    INDEX
    Explanations

    references to attributes of leadership and organizational culture

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

    past states or conditions

    np_acts-logits-general · gemini-2.0-flash

    formerly previously

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.44
    forsch
    -0.43
     '{@
    -0.42
    ğaz
    -0.41
    ăsp
    -0.40
    ciller
    -0.40
    bucht
    -0.40
    kuli
    -0.40
    adering
    -0.39
     Wartawan
    -0.39
    POSITIVE LOGITS
     formerly
    2.78
     Formerly
    2.39
     former
    2.31
    formerly
    2.25
    Formerly
    2.23
     previously
    2.11
     autrefois
    2.09
     Previously
    1.96
     früher
    1.95
    previously
    1.92
    Activations Density 1.168%

    No Known Activations