© 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. 24-GEMMASCOPE-RES-16K
    11. 12446
    Prev
    Next
    INDEX
    Explanations

    references to functions and parameters in programming code

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

    HTML URLs or URL-related strings

    np_acts-logits-general · gemini-2.0-flash

    urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.81
     ProtoMessage
    -0.56
    ignano
    -0.51
     Phase
    -0.50
     Wicidata
    -0.50
    matchCondition
    -0.50
    Referències
    -0.49
    Lähteet
    -0.48
     phase
    -0.48
     Pau
    -0.47
    POSITIVE LOGITS
     url
    3.31
    url
    3.27
     URL
    2.63
    Url
    2.57
    URL
    2.43
     Url
    2.39
     urls
    2.04
     URLs
    1.95
    urls
    1.86
    setUrl
    1.83
    Activations Density 0.080%

    No Known Activations