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. 20-GEMMASCOPE-RES-16K
    6. 1240
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "D" in various contexts

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

    Token "D" followed by various characters/punctuation

    np_acts-logits-general · gemini-2.0-flash

    D. or d followed by punctuation/suffix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.80
    पया
    -0.77
    SOUNDBITE
    -0.73
    Espèce
    -0.73
     HasFactory
    -0.71
     שוליים
    -0.70
    Референце
    -0.70
    AddTagHelper
    -0.70
    ValueStyle
    -0.69
    AccessorTable
    -0.68
    POSITIVE LOGITS
     floor
    0.46
    د
    0.45
     finition
    0.44
     D
    0.44
    fcntl
    0.43
    getRepository
    0.42
    D
    0.41
     barring
    0.41
    Imported
    0.41
    d
    0.41
    Activations Density 0.385%

    No Known Activations