© 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. 22-GEMMASCOPE-RES-16K
    11. 10040
    Prev
    Next
    INDEX
    Explanations

    patterns related to error messages or issues with web requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens before numbers in code or errors

    np_acts-logits-general · gemini-2.0-flash

    error codes 0 3 4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.73
     Meksiku
    -0.70
    λευτα
    -0.58
    XmlAccessorType
    -0.55
    aston
    -0.54
    θε
    -0.53
     actionPerformed
    -0.52
    DC
    -0.52
     DC
    -0.52
    awa
    -0.52
    POSITIVE LOGITS
    tagHelperRunner
    0.79
    ContentAsync
    0.64
    FieldBuilder
    0.62
    μφωνα
    0.53
    Kaynakça
    0.53
     estekak
    0.53
    Lähteet
    0.51
    featureID
    0.47
     Мексичка
    0.46
     BorderSide
    0.46
    Activations Density 0.130%

    No Known Activations