© 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. 15989
    Prev
    Next
    INDEX
    Explanations

    code structures and conditional statements related to data parsing and handling

    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
    aarrggbb
    -0.76
     noqa
    -0.69
     estekak
    -0.60
    exitRule
    -0.55
    цездатний
    -0.55
    basicConfig
    -0.53
     ahol
    -0.51
     zich
    -0.51
     sondern
    -0.51
     suspendu
    -0.51
    POSITIVE LOGITS
    System
    1.37
     System
    1.28
     system
    0.83
     SYSTEM
    0.81
    Syst
    0.77
    ystem
    0.66
    system
    0.65
    )))));
    0.62
     Syst
    0.62
    SYSTEM
    0.61
    Activations Density 0.120%

    No Known Activations