© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12193
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and their variations in context

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

    "num" prefix to variables or parameters

    np_acts-logits-general · gemini-2.0-flash

    num followed by underscore or sol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hauptartikel
    -0.68
    Moda
    -0.57
    ContextHolder
    -0.53
    ════════
    -0.52
     manger
    -0.51
    Awe
    -0.51
    ρίζ
    -0.51
    amiento
    -0.51
     bals
    -0.50
    ฏิ
    -0.50
    POSITIVE LOGITS
     nums
    0.94
     Numa
    0.83
     Num
    0.82
    nums
    0.73
    numRows
    0.71
    httphttps
    0.70
    gum
    0.69
     MainAxisSize
    0.69
     BoxFit
    0.68
     num
    0.67
    Activations Density 0.058%

    No Known Activations