© 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. 4523
    Prev
    Next
    INDEX
    Explanations

    content related to providing advice, particularly legal and personal guidance

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

    words and phrases related to advice, counsel, or professional guidance.

    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
    AnchorStyles
    -0.40
    kwds
    -0.36
     متعلقه
    -0.35
    endwhile
    -0.35
     blast
    -0.35
    يميديا
    -0.35
    IContainer
    -0.35
    rrggbb
    -0.35
     Италијани
    -0.35
    Reagents
    -0.34
    POSITIVE LOGITS
     advice
    2.61
    advice
    2.30
     advise
    2.17
     Advice
    2.16
    Advice
    2.11
     ADVICE
    2.02
     advising
    1.93
     advices
    1.88
     advises
    1.85
     advies
    1.77
    Activations Density 0.370%

    No Known Activations