© 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. 37-GEMMASCOPE-RES-16K
    6. 4344
    Prev
    Next
    INDEX
    Explanations

    key terms related to business management and research publications in a systematic context

    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
     Infórmanos
    -0.50
    WebMethod
    -0.39
    CodeDom
    -0.39
    CrossRef
    -0.38
    internalType
    -0.37
     Exacts
    -0.35
    neté
    -0.34
     propTypes
    -0.34
    __(/*!
    -0.34
    rsiniz
    -0.33
    POSITIVE LOGITS
     focus
    3.52
    focus
    3.06
     Focus
    2.97
     focusing
    2.92
    Focus
    2.88
     focused
    2.84
     focussing
    2.83
     fokus
    2.81
     focuses
    2.78
     focussed
    2.73
    Activations Density 1.019%

    No Known Activations