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. 3038
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to legal terminology and documentation

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

    ending in "ish," "lishes," or "ished."

    np_acts-logits-general · gemini-2.0-flash

    establishes, diminishes, publishes, distinguishes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Haywood
    -0.55
     vierge
    -0.52
    исленность
    -0.51
    gaon
    -0.51
    zole
    -0.49
    hofen
    -0.49
     primaire
    -0.47
     vertes
    -0.47
    grand
    -0.46
     houve
    -0.46
    POSITIVE LOGITS
    ishes
    1.10
    ished
    1.06
    ishing
    1.02
    ishment
    0.98
    isher
    0.94
    ISHING
    0.88
    ISHED
    0.85
    ishments
    0.83
    ish
    0.80
    ishe
    0.80
    Activations Density 0.107%

    No Known Activations