© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 35-GEMMASCOPE-RES-16K
    11. 6486
    Prev
    Next
    INDEX
    Explanations

    concepts related to personal agency and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.67
     CreateTagHelper
    -0.65
     utafitiHapana
    -0.65
    ſelben
    -0.63
     HasFactory
    -0.62
    !*\
    -0.62
    KURZBESCHREIBUNG
    -0.60
     zuſammen
    -0.59
    quiao
    -0.59
     zwiſchen
    -0.59
    POSITIVE LOGITS
    と呼ばれる
    0.33
    MessageOf
    0.33
    jsxFileName
    0.32
    хьтан
    0.30
    DrawerToggle
    0.30
     اص
    0.28
     épaules
    0.28
     ويكيپيديا
    0.28
    biendo
    0.28
    baiki
    0.27
    Activations Density 3.213%

    No Known Activations