© 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. 31-GEMMASCOPE-RES-16K
    6. 2588
    Prev
    Next
    INDEX
    Explanations

    elements related to date handling and time representation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    date and time representations in code (timestamps, date objects, and datetime formats).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.57
    
    -0.56
    LookAnd
    -0.54
     ProtoMessage
    -0.51
    odils
    -0.50
     ExecuteAsync
    -0.49
    NameInMap
    -0.49
    transQ
    -0.48
     színes
    -0.48
    ğraf
    -0.48
    POSITIVE LOGITS
     parse
    0.41
     parsing
    0.40
    parse
    0.38
     gran
    0.36
     parsed
    0.35
     Iso
    0.35
     iso
    0.35
    FormatException
    0.34
    iso
    0.34
     format
    0.34
    Activations Density 0.175%

    No Known Activations