© 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. 6083
    Prev
    Next
    INDEX
    Explanations

    phrases related to reviewing and evaluating documents or information

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

    instructions or directives telling someone to carefully review or examine written material.

    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
    Personendaten
    -0.72
    usermodel
    -0.65
    出版年
    -0.65
     disambiguazione
    -0.63
     nahilalakip
    -0.63
    Aktualisiert
    -0.60
     <=",
    -0.60
    IntoConstraints
    -0.59
     насељу
    -0.58
    ंदीखरीदारी
    -0.57
    POSITIVE LOGITS
     carefully
    2.23
     careful
    1.74
     Carefully
    1.69
    caref
    1.63
     cuidadosamente
    1.55
     Careful
    1.42
     sorgfältig
    1.36
     тщательно
    1.35
     внимательно
    1.34
     attentively
    1.33
    Activations Density 0.359%

    No Known Activations