© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8373
    Prev
    Next
    INDEX
    Explanations

    text related to requests for participation or subscriptions, as well as links to additional content or information

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

    calls-to-action and hyperlinks that direct readers to view more content or information.

    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
    oneofs
    -0.65
    ⓧ
    -0.63
    SourceChecksum
    -0.63
     disambiguazione
    -0.57
    jenige
    -0.50
    EClass
    -0.49
    <?
    -0.49
    ंदीखरीदारी
    -0.48
    libft
    -0.47
     betweenstory
    -0.47
    POSITIVE LOGITS
     full
    0.82
     complete
    0.63
     yourself
    0.63
     FULL
    0.60
     official
    0.60
     fascinating
    0.59
    full
    0.59
     lengkap
    0.55
     vollständ
    0.54
    complete
    0.54
    Activations Density 0.312%

    No Known Activations