© 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. 716
    Prev
    Next
    INDEX
    Explanations

    titles of books or stories

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

    titles of literary works and their associated themes or characters

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

    titles of books and stories

    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
     
    -0.51
    ">:
    -0.45
     serious
    -0.45
    visiae
    -0.43
    richten
    -0.43
    Quanto
    -0.42
     ?
    -0.42
     grade
    -0.42
     right
    -0.42
    poons
    -0.41
    POSITIVE LOGITS
    tvguidetime
    0.90
    mybatisplus
    0.78
     unknownFields
    0.72
    AutoScaleMode
    0.70
    mergeFrom
    0.68
     nahilalakip
    0.68
     MainAxisSize
    0.67
     мәкал
    0.65
    تقاوى
    0.64
     manqué
    0.64
    Activations Density 0.065%

    No Known Activations