© 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. 31-GEMMASCOPE-RES-16K
    11. 12469
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to inventions and their components

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

    references to "the present invention" or patent/technical document terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    phrases that introduce or describe the purpose of a technical invention or innovation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.35
     arşivlendi
    -0.35
    StringUtil
    -0.29
    jangkau
    -0.28
    ً
    -0.28
    IntoConstraints
    -0.28
    DEPORTES
    -0.27
    而又
    -0.27
     δὲ
    -0.26
    ChildScrollView
    -0.26
    POSITIVE LOGITS
    ConstraintMaker
    0.84
    :✨
    0.72
    CloseOperation
    0.71
    setVerticalGroup
    0.70
     surla
    0.69
    Handlung
    0.67
     createSlice
    0.65
    HideFlags
    0.65
     disponibilités
    0.64
    UnusedPrivate
    0.64
    Activations Density 4.163%

    No Known Activations