© 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. 658
    Prev
    Next
    INDEX
    Explanations

    data structure and type-related terms commonly used in programming

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

    programming language constructs related to lists and types

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

    programming data structures and templates

    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
    
    -0.88
    HasAnnotation
    -0.77
    GraphicsUnit
    -0.77
     مرئيه
    -0.72
     autorytatywna
    -0.72
     שוליים
    -0.72
    +#+#
    -0.71
     FetchType
    -0.70
    ]")]
    -0.69
     ProtoMessage
    -0.68
    POSITIVE LOGITS
    <?
    0.66
    erialize
    0.52
    RegistryLite
    0.51
    <?=
    0.50
    WORTH
    0.48
     rendered
    0.45
    istro
    0.44
     <?
    0.44
     SEDS
    0.43
    dhury
    0.42
    Activations Density 0.018%

    No Known Activations