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. 14117
    Prev
    Next
    INDEX
    Explanations

    verb modifiers and particles that define grammatical aspects in a language

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

    Verb tense and transitivity

    np_acts-logits-general · gemini-2.0-flash

    tense, mood, aspect

    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
    uxxxx
    -0.60
    ArrowToggle
    -0.57
    UARY
    -0.56
    endwhile
    -0.54
    SourceChecksum
    -0.53
     okuyayım
    -0.53
     demografica
    -0.52
    chitz
    -0.52
    Geographie
    -0.51
    ècie
    -0.51
    POSITIVE LOGITS
    Past
    0.92
     Present
    0.91
    Present
    0.86
     Past
    0.85
     past
    0.82
     tense
    0.81
    Future
    0.78
     present
    0.78
     PAST
    0.76
     imperfect
    0.75
    Activations Density 0.187%

    No Known Activations