© 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. 1669
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or recommendations

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

    conditional statements or expressions of hypothetical preference using "would" paired with verbs like "like," "rather," "guess," "imagine," or "prefer."

    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
     surla
    -0.68
    Дереккөздер
    -0.56
    endphp
    -0.54
    Smarty
    -0.54
    \{\\
    -0.52
    存于互联网档案馆
    -0.52
    𓃵
    -0.52
    лтемелер
    -0.50
     CURIAM
    -0.50
    IntoConstraints
    -0.49
    POSITIVE LOGITS
     expect
    0.52
     love
    0.52
    expect
    0.45
     argue
    0.44
     gladly
    0.43
     wager
    0.42
     expects
    0.40
     bet
    0.40
     loved
    0.39
     hope
    0.39
    Activations Density 0.144%

    No Known Activations