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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7224
    Prev
    Next
    INDEX
    Explanations

    references to seeds and related concepts

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

    starting with "se" related to seeds or locations

    np_acts-logits-general · gemini-2.0-flash

    seed for transmission or origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.75
    ViewFeatures
    -0.69
     Obrador
    -0.66
    OGND
    -0.66
     Meksiku
    -0.62
    ArrowToggle
    -0.60
    例文帳に追加
    -0.60
     Linus
    -0.59
     Fros
    -0.59
     hechos
    -0.58
    POSITIVE LOGITS
    illots
    0.78
     Seeds
    0.75
     seeds
    0.75
     Seitz
    0.75
    Seeds
    0.74
     Sewell
    0.70
    Se
    0.70
     Seung
    0.69
     sew
    0.68
     sema
    0.66
    Activations Density 0.200%

    No Known Activations