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. 10-GEMMASCOPE-RES-16K
    6. 13193
    Prev
    Next
    INDEX
    Explanations

    details relating to memorial services and funeral announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPATH
    -0.73
     فريبيس
    -0.65
     препратки
    -0.61
    adaptiveStyles
    -0.61
    kloped
    -0.59
    Przypisy
    -0.58
    <?
    -0.58
    MarshalTo
    -0.57
    expandindo
    -0.54
    rstrip
    -0.52
    POSITIVE LOGITS
    Jeografia
    0.61
    uitable
    0.51
    Geplaatst
    0.51
    omock
    0.51
    ransition
    0.50
    ternut
    0.48
     ashore
    0.48
    ronique
    0.47
    ORPG
    0.47
    writerow
    0.47
    Activations Density 0.012%

    No Known Activations