© 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. 11959
    Prev
    Next
    INDEX
    Explanations

    identifiable names or proper nouns, particularly in scientific or literary contexts

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

    author names and citations in academic and technical documents.

    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
     deep
    -0.26
     profondità
    -0.25
     sti
    -0.25
     standing
    -0.24
     impression
    -0.24
     rencontres
    -0.24
     stel
    -0.24
    就
    -0.24
     benefit
    -0.23
    $}}
    -0.23
    POSITIVE LOGITS
     nahilalakip
    0.93
    AsUp
    0.75
    balleur
    0.68
     ujednoznacz
    0.67
    principalColumn
    0.67
     Италијани
    0.66
    Kjelder
    0.65
     utafitiHapana
    0.64
    IntoConstraints
    0.62
    thansa
    0.61
    Activations Density 0.435%

    No Known Activations