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. 5-GEMMASCOPE-RES-16K
    6. 3526
    Prev
    Next
    INDEX
    Explanations

    actions or processes that involve speed and adaptability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.67
    +#+#
    -0.52
    thâu
    -0.50
    avía
    -0.49
     Vor
    -0.47
     selamat
    -0.47
     only
    -0.47
    thoven
    -0.47
     yn
    -0.46
     vart
    -0.46
    POSITIVE LOGITS
     rápidamente
    0.85
    ValueStyle
    0.83
    quickly
    0.81
     quickly
    0.81
     rapidamente
    0.80
     Quickly
    0.80
    quick
    0.80
     Ráp
    0.79
     snabbt
    0.78
     quick
    0.74
    Activations Density 0.354%

    No Known Activations