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. 13-GEMMASCOPE-RES-16K
    6. 147
    Prev
    Next
    INDEX
    Explanations

    terms related to weight, heaviness, and the structural integrity of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    descriptions of weight and balance, often related to handling heavy objects or equipment.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.63
     виправивши
    -0.55
     lenker
    -0.52
    gole
    -0.52
    fico
    -0.49
    AndEndTag
    -0.49
    InjectAttribute
    -0.48
    outi
    -0.47
    erview
    -0.47
    roups
    -0.45
    POSITIVE LOGITS
     weighing
    1.03
     weight
    0.98
     heavier
    0.98
     weighs
    0.93
     weights
    0.91
     heaviest
    0.88
     weigh
    0.84
     weighty
    0.83
    重さ
    0.82
    weigh
    0.81
    Activations Density 0.375%

    No Known Activations