© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 14903
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics related to numerical values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.62
    品
    -0.45
    ge
    -0.45
    t
    -0.44
    w
    -0.43
     dos
    -0.43
    n
    -0.42
    f
    -0.41
    estu
    -0.41
    十四
    -0.41
    POSITIVE LOGITS
    ########.
    1.18
     تضيفلها
    1.08
     resourceCulture
    1.00
    Personensuche
    1.00
     ExecuteAsync
    0.99
    ]='\
    0.98
    superdry
    0.92
     ObjectParameter
    0.92
    expandindo
    0.92
     GenerationType
    0.90
    Activations Density 1.209%

    No Known Activations