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. 18-GEMMASCOPE-RES-16K
    6. 15356
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures and patterns involved in coding and anthropology

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

    before place names

    np_acts-logits-general · gemini-2.0-flash

    Dalhousie University, granulation tissue, SANTA BARBARA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nathalie
    -0.67
     jur
    -0.65
    Notae
    -0.64
    cokinetic
    -0.64
     reflejo
    -0.62
    rouvez
    -0.61
    seido
    -0.61
    rupulous
    -0.61
     jura
    -0.61
     Fath
    -0.61
    POSITIVE LOGITS
    Lynne
    0.85
    WithIOException
    0.85
    Datuak
    0.79
    IContainer
    0.73
    TILE
    0.71
    awtextra
    0.69
    astéro
    0.69
    Rod
    0.68
     Lynne
    0.65
     malt
    0.64
    Activations Density 0.409%

    No Known Activations