© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 7347
    Prev
    Next
    INDEX
    Explanations

    references to technological and medical terms related to monitoring and assessment

    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
     مشين
    -0.37
    бан
    -0.32
     achtergrond
    -0.31
     zuständig
    -0.31
    bubble
    -0.30
    openConnection
    -0.30
     gekomen
    -0.30
     Rücksicht
    -0.29
     Савезне
    -0.29
    fromCharCode
    -0.29
    POSITIVE LOGITS
     BE
    1.86
     Be
    1.75
    BE
    1.70
     Bé
    1.66
    Be
    1.64
     bea
    1.59
     Bea
    1.57
    Bea
    1.57
    Bé
    1.55
    bea
    1.50
    Activations Density 2.240%

    No Known Activations