© 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. 9692
    Prev
    Next
    INDEX
    Explanations

    statistical data related to baseball game performance

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

    before "have," "has," or after a number

    np_acts-logits-general · gemini-2.0-flash

    Royals, Orioles, hander, title

    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
     Whilst
    -1.04
    Whilst
    -1.04
     whilst
    -0.96
    非常的
    -0.71
     amongst
    -0.71
     dibawah
    -0.70
    にて
    -0.68
     Amongst
    -0.67
     didalam
    -0.66
    Pictured
    -0.65
    POSITIVE LOGITS
    OGND
    0.79
    principalColumn
    0.76
     disambiguazione
    0.69
     HttpNotFound
    0.68
    ◗
    0.66
    ReusableCell
    0.66
    цездатний
    0.62
     stället
    0.61
     acaso
    0.59
     ciascuno
    0.59
    Activations Density 0.242%

    No Known Activations