© 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. 8499
    Prev
    Next
    INDEX
    Explanations

    function definitions and parameters in code

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

    Code and logic keywords

    np_acts-logits-general · gemini-2.0-flash

    conditional logic and code keywords

    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
     initComponents
    -0.80
     nahilalakip
    -0.75
     AssemblyCulture
    -0.63
    évaluateur
    -0.62
    sizeCache
    -0.61
     שוליים
    -0.60
    DockStyle
    -0.58
    httphttps
    -0.58
     Faso
    -0.58
     lenker
    -0.57
    POSITIVE LOGITS
     and
    0.86
     or
    0.85
     is
    0.82
     else
    0.67
     then
    0.64
     they
    0.62
     was
    0.55
     <>
    0.52
     than
    0.51
     not
    0.51
    Activations Density 0.099%

    No Known Activations