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. 4443
    Prev
    Next
    INDEX
    Explanations

    quantitative data points and measurements related to various studies

    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
     الحره
    -0.77
    NUMX
    -0.76
     Ngb
    -0.73
    〢
    -0.70
    wahati
    -0.64
     везе
    -0.64
    buro
    -0.63
    rások
    -0.62
    KommentareTeilen
    -0.61
    δή
    -0.60
    POSITIVE LOGITS
    prnewswire
    0.74
    GEBURTSDATUM
    0.57
     kaynağından
    0.57
     kasarigan
    0.55
    :✨
    0.52
     AllAfrica
    0.50
    <strong>
    0.49
    0
    0.47
    >{@
    0.46
     أعلام
    0.45
    Activations Density 0.653%

    No Known Activations