© 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. 870
    Prev
    Next
    INDEX
    Explanations

    time-related concepts and parameters, specifically in a context involving deadlines and durations in milliseconds

    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
     intStringLen
    -0.52
     BoxFit
    -0.45
     Mirror
    -0.45
    ="@+
    -0.45
    sidemargin
    -0.44
    ScopeManager
    -0.43
    Mirror
    -0.43
    IVEREF
    -0.43
    Билгалдахарш
    -0.42
    RuleContext
    -0.41
    POSITIVE LOGITS
     ms
    2.77
     MS
    2.53
     Ms
    2.52
    ms
    2.33
    Ms
    2.27
    MS
    2.23
     MSD
    1.37
     MSF
    1.32
     MSC
    1.32
     MSS
    1.26
    Activations Density 0.505%

    No Known Activations