© 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 - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15970
    Prev
    Next
    INDEX
    Explanations

    conditions or requirements related to permissions or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -1.25
     AssemblyCompany
    -1.17
    tvguidetime
    -1.15
    CppMethod
    -1.08
    IsContent
    -1.03
    ValueStyle
    -1.02
    XtraGrid
    -0.97
    Демографія
    -0.97
    makeConstraints
    -0.95
     كومونز
    -0.95
    POSITIVE LOGITS
     us
    0.74
     people
    0.68
     autor
    0.67
     you
    0.64
     to
    0.63
     individuals
    0.58
     
    0.57
     me
    0.57
     the
    0.54
    uj
    0.53
    Activations Density 0.353%

    No Known Activations