© 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. 4-GEMMASCOPE-RES-16K
    11. 15722
    Prev
    Next
    INDEX
    Explanations

    references to quantities or groups within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...@
    -0.56
    τρ
    -0.55
    mặt
    -0.54
    '){
    -0.53
     can
    -0.52
    Còn
    -0.51
    acyj
    -0.51
     setObject
    -0.50
     kív
    -0.50
    elaar
    -0.48
    POSITIVE LOGITS
     disambiguazione
    0.82
     AssemblyVersion
    0.82
    aarrggbb
    0.80
     transfieras
    0.80
    Clik
    0.79
    oredCriteria
    0.77
    SourceChecksum
    0.76
     فريبيس
    0.75
    Sucesor
    0.75
     cherchés
    0.74
    Activations Density 0.623%

    No Known Activations