© 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. 3947
    Prev
    Next
    INDEX
    Explanations

    elements that indicate conversational style and visual aesthetics in writing

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

    descriptive adjectives and nouns that characterize the quality, style, or distinctive character of something.

    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
    protoimpl
    -0.41
    qxd
    -0.38
    YMS
    -0.36
    তথ্যসূত্র
    -0.35
    ardown
    -0.35
    pport
    -0.35
    Duty
    -0.35
    duty
    -0.34
    Spec
    -0.33
    ayah
    -0.33
    POSITIVE LOGITS
     style
    2.03
     estilo
    1.67
    style
    1.59
     STYLE
    1.55
     styles
    1.55
     Style
    1.54
     stijl
    1.53
    风格
    1.49
     стиль
    1.42
     스타일
    1.38
    Activations Density 0.364%

    No Known Activations