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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9672
    Prev
    Next
    INDEX
    Explanations

    sections related to legal definitions and requirements

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

    legal and regulatory citation formats (section numbers, regulation codes, and statutory references).

    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
     Normdatei
    -0.64
     AssemblyCompany
    -0.63
    AndEndTag
    -0.58
     للاسماء
    -0.58
    XtraReports
    -0.54
     Licence
    -0.52
    RenderAtEndOf
    -0.51
    MENAFN
    -0.51
     محفوظة
    -0.51
     licences
    -0.51
    POSITIVE LOGITS
     дописавши
    0.37
     méd
    0.35
    userLogin
    0.33
     étrangère
    0.33
     catedral
    0.32
    exitRule
    0.32
    richting
    0.32
     capucha
    0.32
    "(
    0.32
    hashtags
    0.31
    Activations Density 1.432%

    No Known Activations