© 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. 20-GEMMASCOPE-RES-16K
    11. 7778
    Prev
    Next
    INDEX
    Explanations

    specific syntax and structure related to coding and programming statements

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

    "sub" as a prefix or a substring

    np_acts-logits-general · gemini-2.0-flash

    words starting with sub

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.77
    aarrggbb
    -0.70
     iprot
    -0.67
    RTEX
    -0.57
     pim
    -0.55
    AnchorStyles
    -0.54
     AssemblyCulture
    -0.53
    CloseOperation
    -0.53
    bitField
    -0.52
    uxxxx
    -0.52
    POSITIVE LOGITS
     sub
    2.50
     Sub
    2.41
     SUB
    2.34
    sub
    2.32
    Sub
    2.31
    SUB
    2.24
     subs
    2.06
     getSub
    2.02
    getSub
    2.01
     Subs
    1.75
    Activations Density 0.244%

    No Known Activations