Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8305
    Prev
    Next
    INDEX
    Explanations

    references to time durations

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

    Time duration before/after an event

    np_acts-logits-general · gemini-2.0-flash

    time durations with temporal qualifiers

    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
    NameInMap
    -0.82
    contentLoaded
    -0.76
     Efq
    -0.75
    IsMutable
    -0.70
    
    -0.69
     Monfieur
    -0.66
    ArrowToggle
    -0.65
    parsedMessage
    -0.64
     estimés
    -0.62
    Хьажоргаш
    -0.61
    POSITIVE LOGITS
     previously
    0.72
    putstr
    0.57
    uver
    0.55
    ukkah
    0.53
     earlier
    0.52
    PhysRev
    0.50
    Vitals
    0.48
     hence
    0.48
    Жен
    0.48
     ear
    0.48
    Activations Density 0.140%

    No Known Activations