© 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. 694
    Prev
    Next
    INDEX
    Explanations

    modal verbs in various contexts

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

    modal verbs and related expressions in the context of permission or capability

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

    his / assigned / his multilingual

    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
    bootstrapcdn
    -0.73
    GeneratedValue
    -0.71
    GeoNames
    -0.68
     فريبيس
    -0.68
     kasarigan
    -0.65
    oa̍t
    -0.63
    TagHelper
    -0.62
    ]")]
    -0.60
     صوتيه
    -0.59
    aktery
    -0.59
    POSITIVE LOGITS
     his
    0.65
    彼の
    0.57
     становника
    0.55
    他的
    0.53
     himself
    0.51
    his
    0.51
     его
    0.50
     him
    0.49
     jeho
    0.48
     jego
    0.48
    Activations Density 0.019%

    No Known Activations