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. 8-GEMMASCOPE-RES-16K
    6. 8018
    Prev
    Next
    INDEX
    Explanations

    comparative differences and variations in data or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lju
    -0.48
    Спољашње
    -0.44
    ونية
    -0.43
    endlich
    -0.41
     erw
    -0.40
     multiple
    -0.40
     status
    -0.39
    copyWith
    -0.39
    пература
    -0.39
     count
    -0.39
    POSITIVE LOGITS
    expandindo
    0.85
     difference
    0.74
    difference
    0.72
     Audiodateien
    0.71
    Difference
    0.70
    xase
    0.70
     Difference
    0.70
     Differences
    0.68
    +:+
    0.66
    ConstraintMaker
    0.65
    Activations Density 1.005%

    No Known Activations