© 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. 39-GEMMASCOPE-RES-16K
    11. 4548
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements and keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.57
     noqa
    -0.56
    IntoConstraints
    -0.54
    Gambas
    -0.51
    enterOuterAlt
    -0.50
    Qed
    -0.50
    binant
    -0.49
    PMailer
    -0.48
    idemiology
    -0.48
    setViewportView
    -0.48
    POSITIVE LOGITS
    mis
    0.30
    interceptors
    0.29
     harina
    0.29
     للاسماء
    0.29
     empresarios
    0.29
     charbon
    0.29
    はん
    0.28
     administrativos
    0.28
    حياتها
    0.28
     Semarang
    0.28
    Activations Density 0.353%

    No Known Activations