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. 14505
    Prev
    Next
    INDEX
    Explanations

    instances of the word "photo" in various contexts

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

    "Photo" or "phot" prefixes

    np_acts-logits-general · gemini-2.0-flash

    photographic terms

    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
     MainAxisSize
    -0.72
    írus
    -0.62
    soever
    -0.61
    verages
    -0.56
    DataOutputStream
    -0.55
    ANCE
    -0.55
    fulness
    -0.53
     onCreateView
    -0.52
    fromLTRB
    -0.52
    FindBy
    -0.51
    POSITIVE LOGITS
     pinulongan
    0.88
    참고
    0.64
    hopped
    0.63
    graphed
    0.62
     shoots
    0.61
    GroupLayout
    0.59
    fjspx
    0.58
     shoot
    0.57
     propOrder
    0.57
     Wikimédia
    0.57
    Activations Density 0.074%

    No Known Activations