© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 7958
    Prev
    Next
    INDEX
    Explanations

    mentions of bodies of water, specifically rivers and oceans

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

    following "River" or "Ocean"

    np_acts-logits-general · gemini-2.0-flash

    river and ocean features

    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
     تضيفلها
    -0.80
    裟
    -0.65
     themſelves
    -0.65
     esboço
    -0.63
     Roskov
    -0.61
    CloseOperation
    -0.60
    Aktualisiert
    -0.60
     uintptr
    -0.60
     ***!
    -0.60
     >=",
    -0.59
    POSITIVE LOGITS
     Region
    0.68
    thâu
    0.63
    pherd
    0.63
     endregion
    0.60
     Regions
    0.59
    front
    0.58
    side
    0.58
     country
    0.57
     region
    0.57
     ocean
    0.56
    Activations Density 0.122%

    No Known Activations