© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14660
    Prev
    Next
    INDEX
    Explanations

    technical terms and coding structures related to software and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.76
    AndEndTag
    -0.72
     GetEnumerator
    -0.70
    rinfo
    -0.69
     autorytatywna
    -0.68
    󠁿
    -0.67
    rostis
    -0.66
    couts
    -0.66
    DNEY
    -0.65
    ➟
    -0.63
    POSITIVE LOGITS
    Graphics
    0.68
     Graphics
    0.66
     graphics
    0.65
    TL
    0.63
    graphics
    0.59
     Schilling
    0.59
    tl
    0.57
    uri
    0.56
    kr
    0.55
     colspan
    0.54
    Activations Density 2.713%

    No Known Activations