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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 2302
    Prev
    Next
    INDEX
    Explanations

    the act of walking or related actions

    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
     %>%
    -0.57
    astronomie
    -0.54
    RoutingModule
    -0.54
    spesies
    -0.54
     "];
    -0.52
    raszam
    -0.51
     <?=
    -0.50
    éhez
    -0.49
    شاركة
    -0.49
    mography
    -0.49
    POSITIVE LOGITS
     autorytatywna
    1.28
    tagHelperRunner
    0.98
     walked
    0.91
    bootstrapcdn
    0.88
    Walk
    0.86
    WALK
    0.85
     walking
    0.84
    walk
    0.84
     walks
    0.84
    Walking
    0.84
    Activations Density 0.224%

    No Known Activations