© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 3637
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to programming or computing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentAsync
    -0.74
    expandindo
    -0.70
     CreateTagHelper
    -0.64
     consultato
    -0.63
    Населення
    -0.61
    клопе
    -0.60
    Referències
    -0.60
     surla
    -0.58
    PYX
    -0.57
    RenderAtEndOf
    -0.56
    POSITIVE LOGITS
     članak
    0.60
     slavery
    0.55
    Cable
    0.54
    lager
    0.54
     Cable
    0.54
     abuse
    0.53
     tents
    0.53
     Abuse
    0.50
     Slavery
    0.50
     fusca
    0.50
    Activations Density 1.907%

    No Known Activations