© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8833
    Prev
    Next
    INDEX
    Explanations

    co-occurrence of conjunctions and references in contexts discussing potential risks or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insegna
    -0.56
    randomUUID
    -0.52
    cartão
    -0.51
     fatica
    -0.51
    ếp
    -0.50
     sanitaires
    -0.49
    InputBorder
    -0.48
    escudo
    -0.48
    Билгалдахарш
    -0.48
    RectangleBorder
    -0.48
    POSITIVE LOGITS
    setupUi
    0.67
    帖最后由
    0.63
    AddRange
    0.61
    dhist
    0.60
    DispatchToProps
    0.59
     CreateTagHelper
    0.58
    ropical
    0.58
    oa̍t
    0.55
     VizieR
    0.54
    ariste
    0.53
    Activations Density 0.348%

    No Known Activations