© 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. 2478
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completion or resolution

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

    words and phrases that convey completeness, totality, or comprehensive scope (such as "exactly," "all," "one of the," "together," "all in this").

    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
     “
    -0.39
     gefü
    -0.33
    バ
    -0.30
    ++;
    -0.30
     fl
    -0.30
    Ba
    -0.29
     rail
    -0.29
     fit
    -0.29
     ar
    -0.29
     linear
    -0.29
    POSITIVE LOGITS
    Personendaten
    1.05
    rungsseite
    0.90
    SequentialGroup
    0.78
     HasFactory
    0.71
     FetchType
    0.69
    FXMLLoader
    0.67
    CloseOperation
    0.65
    脚注の使い方
    0.63
     Préférences
    0.63
    typeorm
    0.62
    Activations Density 0.037%

    No Known Activations