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. 11083
    Prev
    Next
    INDEX
    Explanations

    competitive elements and references to events or tournaments

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

    Follows a noun, often a person

    np_acts-logits-general · gemini-2.0-flash

    assigned participant

    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
    expandindo
    -0.75
    IUrlHelper
    -0.72
     Италијани
    -0.60
    clat
    -0.60
     estekak
    -0.59
    SourceChecksum
    -0.58
     ingrat
    -0.57
    parseFrom
    -0.56
     Anis
    -0.55
    тьи
    -0.54
    POSITIVE LOGITS
     whoever
    0.97
     Whoever
    0.93
    Whoever
    0.88
     assigned
    0.83
     whome
    0.81
     designated
    0.81
     each
    0.78
     whichever
    0.75
    designated
    0.73
     clockwise
    0.72
    Activations Density 0.381%

    No Known Activations