© 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. 38-GEMMASCOPE-RES-16K
    11. 16217
    Prev
    Next
    INDEX
    Explanations

    technical expressions and mathematical variables related to magnetization and field theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    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
    -0.60
    :✨
    -0.53
     Audiodateien
    -0.48
    ResumeLayout
    -0.47
     Kunt
    -0.46
    providedIn
    -0.45
    ביוגרפיה
    -0.45
    IntoConstraints
    -0.45
    hyrchwyd
    -0.44
     useRef
    -0.43
    POSITIVE LOGITS
    mathbf
    0.77
     **
    0.74
     mathvariant
    0.64
    boldsymbol
    0.60
    <b>
    0.59
    **
    0.56
    textbf
    0.55
    <strong>
    0.53
    bf
    0.52
     $\
    0.49
    Activations Density 1.288%

    No Known Activations