Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5342
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses

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

    URLs (often with ://)

    np_acts-logits-general · gemini-2.0-flash

    URLs, localhost, script, api

    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
    存于互联网档案馆
    -0.47
    guri
    -0.47
    "]);
    
    -0.46
     ligaments
    -0.44
    ExecuteReader
    -0.44
    tonsoft
    -0.44
    raisemb
    -0.44
    ✭✭
    -0.42
    setOptions
    -0.41
    Recuper
    -0.40
    POSITIVE LOGITS
    localhost
    0.89
     Roskov
    0.83
     nakalista
    0.81
     localhost
    0.69
    новниш
    0.68
    Carriera
    0.67
    ьаж
    0.66
    Kariera
    0.64
    devamını
    0.62
    sizeCache
    0.60
    Activations Density 0.112%

    No Known Activations