© 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. 17-GEMMASCOPE-RES-16K
    11. 6102
    Prev
    Next
    INDEX
    Explanations

    attributes related to layout and size specifications in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.71
    Izvori
    -0.66
    gameserver
    -0.63
     level
    -0.60
    ɵɵ
    -0.57
     вікі
    -0.57
    исленность
    -0.55
     propOrder
    -0.55
    POUND
    -0.55
    TabIndex
    -0.54
    POSITIVE LOGITS
     Ministerial
    0.62
    sizeof
    0.57
     horizontally
    0.56
     ministerial
    0.56
     initials
    0.55
     Stip
    0.55
     width
    0.54
     sizeof
    0.54
     Width
    0.53
     ancho
    0.53
    Activations Density 0.154%

    No Known Activations