© 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. 18-GEMMASCOPE-RES-16K
    11. 8970
    Prev
    Next
    INDEX
    Explanations

    references to specific names and locations, particularly related to "Jefferson."

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

    Names followed by locations

    np_acts-logits-general · gemini-2.0-flash

    Alice and Jefferson names

    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
     AssemblyProduct
    -1.10
     Bergh
    -0.85
    PathParam
    -0.77
     Moulton
    -0.75
     Martyn
    -0.73
     Alpen
    -0.71
    propTypes
    -0.70
     Kieran
    -0.69
    setScene
    -0.69
    writeFieldEnd
    -0.68
    POSITIVE LOGITS
     Ithaca
    0.67
     Esau
    0.65
    ivory
    0.65
    paravant
    0.64
     simplifié
    0.63
    licitud
    0.62
    xFF
    0.59
    ombies
    0.59
     GOB
    0.58
     acetic
    0.58
    Activations Density 0.573%

    No Known Activations