© 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. 19-GEMMASCOPE-RES-16K
    11. 1704
    Prev
    Next
    INDEX
    Explanations

    links and references to resources or examples in documentation or tutorials

    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
    '},
    -0.84
    DeleteBehavior
    -0.72
    AlterField
    -0.67
     }</
    -0.67
    loài
    -0.66
     RemoteException
    -0.65
     disambiguazione
    -0.64
    !';
    -0.64
    %");
    -0.63
     بيها
    -0.63
    POSITIVE LOGITS
     https
    3.24
     http
    3.20
    https
    3.02
    http
    3.01
     www
    2.26
    ttps
    1.98
    www
    1.94
    Https
    1.47
    ttp
    1.39
     Http
    1.26
    Activations Density 0.860%

    No Known Activations