© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 619
    Prev
    Next
    INDEX
    Explanations

    references to measurements and optical signals

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

    terms related to measurements and characteristics in optical systems

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

    character or characteristic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.69
     estekak
    -0.53
    UrlResolution
    -0.49
    دانشنامهٔ
    -0.48
     disambiguazione
    -0.47
    insky
    -0.47
    cough
    -0.46
     Buried
    -0.46
     núi
    -0.45
    Personendaten
    -0.44
    POSITIVE LOGITS
     character
    2.65
     char
    2.61
     Character
    2.53
    Char
    2.48
    char
    2.45
    character
    2.40
     Char
    2.40
     CHAR
    2.38
    Character
    2.38
     CHARACTER
    2.35
    Activations Density 0.076%

    No Known Activations