© 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. 643
    Prev
    Next
    INDEX
    Explanations

    references to specific programming constructs or test assertions

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

    references to errors in programming or technical contexts

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

    code language and technical terms

    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
     OFDb
    -0.72
     فريبيس
    -0.64
    nocache
    -0.60
     &___
    -0.54
     Meilleur
    -0.52
                                   
    -0.51
    -0.49
    -0.48
    UnusedPrivate
    -0.48
    يميديا
    -0.48
    POSITIVE LOGITS
    SOUNDBITE
    0.59
    مقاله
    0.55
     مُعرِّف
    0.54
    cellona
    0.54
    SequentialGroup
    0.54
     stanov
    0.53
    riman
    0.52
    ỳnh
    0.52
    θέ
    0.52
    Notae
    0.51
    Activations Density 0.020%

    No Known Activations