© 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. 30-GEMMASCOPE-RES-16K
    11. 12547
    Prev
    Next
    INDEX
    Explanations

    action-oriented phrases involving movement or commands

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

    Infinitive marker "to" followed by certain verbs

    np_acts-logits-general · gemini-2.0-flash

    to followed by verb

    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
     viajar
    -0.69
     Ruang
    -0.65
     viaja
    -0.62
     $_"
    -0.60
     ainfi
    -0.60
     otomatig
    -0.60
     viajes
    -0.58
    routeProvider
    -0.57
    stateProvider
    -0.57
     traveled
    -0.57
    POSITIVE LOGITS
     pick
    0.46
     inspect
    0.44
     check
    0.43
     ब्रेकडाउन
    0.42
     see
    0.40
     arşivlendi
    0.38
     witness
    0.38
     announce
    0.38
    queryInterface
    0.37
     discuss
    0.37
    Activations Density 0.281%

    No Known Activations