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. 15775
    Prev
    Next
    INDEX
    Explanations

    elements related to significant events or conditions in a narrative

    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
    ')):
    -0.49
    بوابة
    -0.48
     ffilmiau
    -0.47
     Village
    -0.46
    \#:
    -0.45
    haria
    -0.45
    érien
    -0.45
    )|^{
    -0.44
     Pays
    -0.44
    ínguez
    -0.43
    POSITIVE LOGITS
    TypedDataSet
    0.78
    contentLoaded
    0.74
    UnusedPrivate
    0.71
    Jeografia
    0.68
    Personensuche
    0.67
    RenderAtEndOf
    0.66
     Winaray
    0.66
    RTGC
    0.63
    __;
    0.62
    adaptiveStyles
    0.62
    Activations Density 0.768%

    No Known Activations