© 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. 689
    Prev
    Next
    INDEX
    Explanations

    sequences of formatting and coding elements, primarily related to lists or structured data

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

    instances of references and citations in technical documents

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

    citation references `[@`

    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
     مرئيه
    -0.92
    IUrlHelper
    -0.87
     referenties
    -0.82
    ंदीखरीदारी
    -0.79
     مشين
    -0.79
     oprot
    -0.78
    yntaxException
    -0.72
     <=",
    -0.71
    LookAnd
    -0.71
    ThroughAttribute
    -0.69
    POSITIVE LOGITS
     leaſt
    1.01
     houſe
    1.01
     Houſe
    0.99
     pleaſure
    0.95
     Diſ
    0.94
     avoient
    0.93
     ſec
    0.93
     obſ
    0.93
     ſon
    0.93
     auroit
    0.92
    Activations Density 0.917%

    No Known Activations