© 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. 24-GEMMASCOPE-RES-16K
    11. 8513
    Prev
    Next
    INDEX
    Explanations

    components related to graphical user interface elements or classes

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

    Strings followed by "if" or "e" tokens

    np_acts-logits-general · gemini-2.0-flash

    local limits lease policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reportWebVitals
    -0.62
     CURLOPT
    -0.57
     tunn
    -0.52
    fflush
    -0.50
     StatelessWidget
    -0.49
    else
    -0.48
    Искәрмәләр
    -0.47
    DockStyle
    -0.47
     EClass
    -0.46
    onomi
    -0.46
    POSITIVE LOGITS
     للمعارف
    0.79
    ineno
    0.67
    ocal
    0.64
    imit
    0.63
     defaultstate
    0.60
    inks
    0.59
    earn
    0.59
    ocation
    0.58
    anguage
    0.58
     متعلقه
    0.57
    Activations Density 0.314%

    No Known Activations