© 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 EvalsExportsAPI 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. 12445
    Prev
    Next
    INDEX
    Explanations

    elements related to probability and statistical analysis

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

    Numbers or ratios

    np_acts-logits-general · gemini-2.0-flash

    probability calculations

    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
     hundred
    -0.63
     Eighty
    -0.63
    Fifty
    -0.62
     Fifty
    -0.61
     Thirty
    -0.59
     Sixty
    -0.58
    ItemBackground
    -0.57
    addGap
    -0.57
    Thirty
    -0.53
     Forty
    -0.52
    POSITIVE LOGITS
    complexContent
    0.82
     three
    0.73
     two
    0.68
     deux
    0.65
     four
    0.64
     trois
    0.63
    abestanden
    0.63
     one
    0.59
     dois
    0.59
     
    0.57
    Activations Density 1.415%

    No Known Activations