© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8205
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with electronic circuits and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FunctionFlags
    -0.83
    Билгалдахарш
    -0.71
     Мексичка
    -0.65
     незавершена
    -0.61
    windowFixed
    -0.59
    хьтан
    -0.57
    ukunft
    -0.56
     soutenu
    -0.54
     Audiodateien
    -0.54
     abierta
    -0.54
    POSITIVE LOGITS
     sensor
    0.73
     detector
    0.69
    StoryboardSegue
    0.68
     sensors
    0.66
     device
    0.63
     detectors
    0.60
     module
    0.60
     electronic
    0.60
     unit
    0.59
     controller
    0.59
    Activations Density 1.218%

    No Known Activations