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. 22-GEMMASCOPE-RES-16K
    6. 13060
    Prev
    Next
    INDEX
    Explanations

    mentions of photographs or photo-related content

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

    Photography and photolithography

    np_acts-logits-general · gemini-2.0-flash

    technical photo compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.84
    soever
    -0.77
     transfieras
    -0.68
    fulness
    -0.66
    verages
    -0.65
    Diweddarwch
    -0.62
    enumi
    -0.61
    írus
    -0.61
    drawal
    -0.61
    routeProvider
    -0.61
    POSITIVE LOGITS
     shoots
    0.64
    realistic
    0.63
    graphed
    0.63
    hopped
    0.62
     shoot
    0.61
     ops
    0.60
     volta
    0.57
    graphs
    0.57
     taken
    0.54
    booth
    0.54
    Activations Density 0.067%

    No Known Activations