© 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. 37-GEMMASCOPE-RES-16K
    11. 533
    Prev
    Next
    INDEX
    Explanations

    XML parameters and global variables in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.66
    IntoConstraints
    -0.53
    AnchorStyles
    -0.49
    oneofs
    -0.49
     فريبيس
    -0.47
     GenerationType
    -0.42
    Hentet
    -0.42
     TextInputType
    -0.41
     considérons
    -0.41
    VersionUID
    -0.40
    POSITIVE LOGITS
     global
    3.77
    global
    3.36
     Global
    3.34
    Global
    3.17
     GLOBAL
    2.95
     globale
    2.77
    GLOBAL
    2.72
     globales
    2.70
     глоба
    2.69
     globally
    2.64
    Activations Density 0.351%

    No Known Activations