© 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. 17-GEMMASCOPE-RES-16K
    6. 4684
    Prev
    Next
    INDEX
    Explanations

    references to specific articles, documents, or sections within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.80
     resourceCulture
    -0.79
    +:+
    -0.73
     GenerationType
    -0.66
    GraphicsUnit
    -0.65
     bezeichneter
    -0.63
    tagHelperRunner
    -0.62
    таратура
    -0.60
    rrggbb
    -0.59
    URLException
    -0.59
    POSITIVE LOGITS
     full
    1.93
    full
    1.67
    Full
    1.66
     Full
    1.54
    FULL
    1.54
     FULL
    1.50
     complete
    1.36
     volledige
    1.33
     vollständige
    1.16
    complete
    1.14
    Activations Density 0.325%

    No Known Activations