© 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. 10808
    Prev
    Next
    INDEX
    Explanations

    references to modal verbs and their structures in sentences

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

    German words and phrases related to verbs, sentence construction, and grammatical concepts.

    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
    sprogramm
    -0.36
    middels
    -0.35
     makhluk
    -0.33
     nôtre
    -0.32
    endmodule
    -0.32
     которое
    -0.32
    glied
    -0.31
    liothè
    -0.31
     Оно
    -0.31
    anskje
    -0.31
    POSITIVE LOGITS
     propOrder
    0.68
    ReusableCell
    0.68
    AddTagHelper
    0.62
    InSection
    0.58
    ValueStyle
    0.58
    RotationOrder
    0.57
    TypedDataSet
    0.57
    inSlope
    0.53
    IntoConstraints
    0.53
    homonymie
    0.52
    Activations Density 0.007%

    No Known Activations