© 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. 5146
    Prev
    Next
    INDEX
    Explanations

    queries for assistance and expressions of hope or uncertainty

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

    question words and requests for help in online forums and discussions.

    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
    featureID
    -0.28
     ziren
    -0.27
     suas
    -0.26
    Siblings
    -0.26
    lük
    -0.26
     tutte
    -0.26
     uniform
    -0.25
    mları
    -0.24
     ogól
    -0.24
    たちに
    -0.24
    POSITIVE LOGITS
     someone
    3.50
    someone
    3.31
     somebody
    3.19
    Someone
    3.09
     Someone
    3.02
    somebody
    2.91
     alguien
    2.73
     Somebody
    2.69
    Somebody
    2.64
     SOMEONE
    2.64
    Activations Density 0.740%

    No Known Activations