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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 5958
    Prev
    Next
    INDEX
    Explanations

    instances of the word "team" and its variations

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

    "team"

    np_acts-logits-general · gemini-2.0-flash

    team members and projects

    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
    enumi
    -0.80
     pinulongan
    -0.72
    richTextPanel
    -0.70
    bootstrapcdn
    -0.70
     rootReducer
    -0.64
    ۪
    -0.64
    TargetException
    -0.63
    省市镇
    -0.63
    rhosis
    -0.61
     térmica
    -0.61
    POSITIVE LOGITS
     members
    0.82
     elbise
    0.76
     captain
    0.75
     captains
    0.73
    spirit
    0.73
    mates
    0.71
     member
    0.69
     spirit
    0.69
     effort
    0.68
    member
    0.68
    Activations Density 0.040%

    No Known Activations