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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 8133
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mathematical concepts and engineering processes

    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
    racy
    -0.62
     Bet
    -0.57
     
    -0.54
     (
    -0.53
     area
    -0.52
    GED
    -0.52
     op
    -0.51
    חים
    -0.48
     A
    -0.48
     So
    -0.48
    POSITIVE LOGITS
     Monfieur
    1.21
     Diſ
    1.03
     Anſ
    1.03
     Efq
    0.98
     Reſ
    0.97
     myſelf
    0.97
     Theſe
    0.94
     pleaſure
    0.91
     Eſ
    0.90
    ſelf
    0.89
    Activations Density 0.186%

    No Known Activations