© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6204
    Prev
    Next
    INDEX
    Explanations

    key details related to promotions, career movements, and historical timelines

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

    a change in role or position

    np_acts-logits-general · gemini-2.0-flash

    career transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hauptartikel
    -0.30
    formik
    -0.30
     enfans
    -0.28
     végét
    -0.28
     gada
    -0.27
    şağı
    -0.27
    ("")]
    -0.26
    TestTools
    -0.26
    一来
    -0.26
    就这么
    -0.25
    POSITIVE LOGITS
     shifted
    1.32
     transitioned
    1.29
     switched
    1.26
     switching
    1.23
    Switching
    1.21
     transferred
    1.20
     transitioning
    1.19
     Switching
    1.16
     moved
    1.15
    switching
    1.13
    Activations Density 0.600%

    No Known Activations