© 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. 13621
    Prev
    Next
    INDEX
    Explanations

    requests for feedback and assistance

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

    polite closing phrases expressing gratitude or welcoming sentiment.

    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
    Hochspringen
    -0.42
     Existence
    -0.35
    labelledby
    -0.33
     UT
    -0.33
     Force
    -0.33
    Fak
    -0.32
    vency
    -0.32
    aut
    -0.32
    corresponding
    -0.31
    UPAC
    -0.31
    POSITIVE LOGITS
     welcome
    1.34
     welcomed
    1.21
     willkommen
    1.09
    welcome
    1.08
     encouraged
    1.07
     welkom
    1.06
     WELCOME
    1.04
     Welcome
    0.98
    Welcome
    0.97
     appreciated
    0.96
    Activations Density 0.305%

    No Known Activations