© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15740
    Prev
    Next
    INDEX
    Explanations

    historical references related to specific regions, especially concerning Schleswig and Holstein, and their political contexts

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

    Historical periods or events

    np_acts-logits-general · gemini-2.0-flash

    Schleswig-Holstein historical periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    readystatechange
    -0.60
    astify
    -0.57
    ordano
    -0.53
    mybatisplus
    -0.52
    ChildScrollView
    -0.50
    openhauer
    -0.50
    DispatchToProps
    -0.49
    hoeddwyd
    -0.48
    ंदीखरीदारी
    -0.47
     cherchés
    -0.47
    POSITIVE LOGITS
     period
    0.90
     Period
    0.90
     era
    0.76
     Era
    0.76
    period
    0.74
    Period
    0.74
     PERIOD
    0.67
     periode
    0.66
     periods
    0.61
     Periods
    0.61
    Activations Density 0.452%

    No Known Activations