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. 10341
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to art and its market

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

    before verbs and adjectives

    np_acts-logits-general · gemini-2.0-flash

    share informationFalling Skiesyou liketo live

    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
     становника
    -0.72
     تانيه
    -0.70
    pushFollow
    -0.70
     resourceCulture
    -0.69
    ⓧ
    -0.69
    ViewInit
    -0.67
    SBATCH
    -0.63
    ็จ
    -0.62
     صوتيه
    -0.62
    WriteAttribute
    -0.61
    POSITIVE LOGITS
     vivido
    0.50
     vivere
    0.49
    \|_{\
    0.49
    новништво
    0.45
     vicissitudes
    0.45
     compréhension
    0.43
     profond
    0.43
     brillante
    0.42
     vivir
    0.42
    vers
    0.42
    Activations Density 0.076%

    No Known Activations