© 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. 10740
    Prev
    Next
    INDEX
    Explanations

    terms related to coupling mechanisms in assembly or mechanical systems

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

    "[something] state" or "[something] position" phrases

    np_acts-logits-general · gemini-2.0-flash

    states of being

    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
    ########.
    -0.59
    Personensuche
    -0.54
    IntoConstraints
    -0.41
    libft
    -0.39
    onOptions
    -0.39
     noDo
    -0.38
    VersionUID
    -0.38
    LEGGI
    -0.37
    GetAxis
    -0.37
    MessageOf
    -0.37
    POSITIVE LOGITS
     state
    1.30
     estado
    1.29
    状态
    1.23
     상태
    1.23
     Zustand
    1.21
     states
    1.20
     état
    1.18
     состояния
    1.14
     состояние
    1.13
    狀態
    1.12
    Activations Density 1.215%

    No Known Activations