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. 0-GEMMASCOPE-RES-16K
    6. 6974
    Prev
    Next
    INDEX
    Explanations

    terms related to jumps or significant changes, particularly in a context involving oil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufig
    -0.53
    geführten
    -0.52
    cor
    -0.48
    gestellten
    -0.47
    getActive
    -0.47
    Mat
    -0.47
    ไข
    -0.47
    lardır
    -0.47
    erdings
    -0.47
     mat
    -0.46
    POSITIVE LOGITS
     jumps
    1.09
    amount
    1.08
     Amount
    0.95
    jumps
    0.88
    Amount
    0.88
     jumping
    0.88
    +#+#
    0.87
     Jumps
    0.86
     amount
    0.85
    jumping
    0.82
    Activations Density 0.088%

    No Known Activations