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. 16-GEMMASCOPE-RES-16K
    6. 571
    Prev
    Next
    INDEX
    Explanations

    instances of significant or notable events or actions

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

    Land use, habitation, or occupancy

    np_acts-logits-general · gemini-2.0-flash

    occupants of residences or land

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.90
     виправивши
    -0.84
    ConstraintMaker
    -0.80
    sidemargin
    -0.77
     للمعارف
    -0.74
     lenker
    -0.74
    RenderAtEndOf
    -0.74
    EndContext
    -0.74
    دانشنامهٔ
    -0.73
    styleType
    -0.72
    POSITIVE LOGITS
     occupants
    0.92
     tenants
    0.90
     occupant
    0.81
     occupancy
    0.79
     tenant
    0.75
     occup
    0.69
    occup
    0.65
     occupation
    0.64
     Tenants
    0.63
     visitors
    0.61
    Activations Density 0.473%

    No Known Activations