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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-GEMMASCOPE-RES-16K
    6. 8984
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to tools and fasteners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TemporalType
    -0.75
    ArgsConstructor
    -0.62
     pinulongan
    -0.62
    RetentionPolicy
    -0.61
    onAttach
    -0.61
     виправивши
    -0.59
     ModelExpression
    -0.58
     Picchu
    -0.58
    mentaux
    -0.58
     AspNetCore
    -0.57
    POSITIVE LOGITS
     pliers
    0.78
     pry
    0.66
     wrench
    0.62
     multime
    0.62
     wren
    0.61
     vice
    0.59
     screwdriver
    0.58
    plier
    0.58
     span
    0.56
     ratchet
    0.54
    Activations Density 0.173%

    No Known Activations