© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14318
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and legal cases

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

    institutional names and affiliations, particularly "Clayman Institute" and related academic/organizational titles.

    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
    IntoConstraints
    -0.67
    RTLR
    -0.60
     MainAxisSize
    -0.59
    findpost
    -0.58
    rungsseite
    -0.58
    HtmlAttribute
    -0.58
     wireType
    -0.57
    PropertyChanging
    -0.56
    GTCX
    -0.55
     initComponents
    -0.54
    POSITIVE LOGITS
    참고
    0.42
     souple
    0.37
     vandens
    0.35
     sentiers
    0.35
     liderança
    0.34
     udział
    0.34
    throwable
    0.33
     personajes
    0.33
     yardım
    0.32
     húmedo
    0.32
    Activations Density 0.611%

    No Known Activations