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. 5-GEMMASCOPE-RES-16K
    6. 1995
    Prev
    Next
    INDEX
    Explanations

    terms related to strength and its various attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gub
    -0.73
    раздо
    -0.73
     Wyman
    -0.73
     Abar
    -0.73
    Portale
    -0.71
     Wylie
    -0.71
     alibi
    -0.71
     Dowling
    -0.70
     Mase
    -0.69
    Vod
    -0.69
    POSITIVE LOGITS
     strength
    1.84
     Strength
    1.81
    strength
    1.79
     STRENGTH
    1.73
    Strength
    1.63
    STRENGTH
    1.60
     strengths
    1.56
    ngths
    1.47
     streng
    1.37
     Strengths
    1.35
    Activations Density 0.054%

    No Known Activations