© 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. 37-GEMMASCOPE-RES-16K
    11. 3879
    Prev
    Next
    INDEX
    Explanations

    technical terms related to chemical reactions and materials in industrial contexts

    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
    ××
    -0.60
    SRS
    -0.58
    CSP
    -0.56
    PPS
    -0.56
    PAM
    -0.56
     PPR
    -0.55
     PSM
    -0.55
     CVC
    -0.55
    CCS
    -0.54
    CPS
    -0.54
    POSITIVE LOGITS
     ainfi
    0.73
     desmotivaciones
    0.71
     técn
    0.69
     Einfluß
    0.68
     miniaturka
    0.65
     tuyo
    0.64
     avoient
    0.63
     tatuagens
    0.63
     TÉCN
    0.62
     pérd
    0.62
    Activations Density 3.131%

    No Known Activations