Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 410
    Prev
    Next
    INDEX
    Explanations

    expressions of perception and testimony concerning behavior and experience

    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
     referenties
    -0.76
     MaterialApp
    -0.65
     protoimpl
    -0.61
    ]='\
    -0.56
     ویکی‌پدیای
    -0.54
    Portale
    -0.53
    didSet
    -0.52
    تقاوى
    -0.51
    ichord
    -0.51
    arschijnlijk
    -0.51
    POSITIVE LOGITS
     seeing
    2.34
     sees
    2.11
     saw
    2.07
     see
    2.00
    seeing
    1.97
     seen
    1.91
     Seeing
    1.90
    Seeing
    1.85
     hearing
    1.73
     witnessing
    1.70
    Activations Density 0.485%

    No Known Activations