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. 20-GEMMASCOPE-RES-16K
    6. 10204
    Prev
    Next
    INDEX
    Explanations

    gerunds and present participles that indicate ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.89
     skimage
    -0.63
    OptionsMenu
    -0.62
    stdafx
    -0.59
     getItemId
    -0.58
    reciate
    -0.56
    setopt
    -0.56
     getRule
    -0.56
     SIMBAD
    -0.55
    льевич
    -0.55
    POSITIVE LOGITS
    ly
    1.03
    ging
    0.90
    ting
    0.89
    LY
    0.87
    izing
    0.82
    gggg
    0.82
    GGGG
    0.81
    ating
    0.81
    ggg
    0.77
    cting
    0.76
    Activations Density 0.680%

    No Known Activations