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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4167
    Prev
    Next
    INDEX
    Explanations

    statistical data related to temperature changes and climate impact

    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
    RenderAtEndOf
    -0.68
     estimés
    -0.62
    findpost
    -0.49
     Vergangenheit
    -0.47
    tagHelperRunner
    -0.47
    </thead>
    -0.46
    aughey
    -0.46
     trajets
    -0.45
     szklan
    -0.45
     thous
    -0.44
    POSITIVE LOGITS
    featureID
    0.75
     Normdatei
    0.70
     Walkover
    0.69
    niająca
    0.63
     McRae
    0.62
     Signalez
    0.61
    orsese
    0.61
     Preferencias
    0.59
     uska
    0.57
    gway
    0.57
    Activations Density 1.239%

    No Known Activations