© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7020
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluating arguments and decision-making

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

    words and phrases related to critical analysis, evaluation, and assessment of information quality.

    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
     curated
    -0.45
    /**
    -0.41
     strip
    -0.38
     disponibilités
    -0.38
    FlatAppearance
    -0.35
     prospec
    -0.35
     curate
    -0.35
     intermedi
    -0.34
     culture
    -0.34
     STRIP
    -0.34
    POSITIVE LOGITS
    ArrowToggle
    0.58
    IVEREF
    0.54
     rhetorical
    0.51
    ритори
    0.50
     Rhetor
    0.50
     Tone
    0.48
     sentence
    0.48
    gebob
    0.47
    ELTS
    0.47
    Tone
    0.46
    Activations Density 0.489%

    No Known Activations