© 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. 21-GEMMASCOPE-RES-16K
    6. 7912
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.74
    ActionCreators
    -0.74
    tance
    -0.71
    DataAnnotations
    -0.69
    SessionFactory
    -0.66
    damente
    -0.64
    mapStateToProps
    -0.64
    QMetaType
    -0.64
    schild
    -0.63
    MLLoader
    -0.61
    POSITIVE LOGITS
    ning
    0.67
    ek
    0.65
    ext
    0.58
    eken
    0.58
    ews
    0.56
    ew
    0.55
    ey
    0.54
    umber
    0.52
    nnn
    0.52
    na
    0.51
    Activations Density 0.348%

    No Known Activations