© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2635
    Prev
    Next
    INDEX
    Explanations

    scientific classifications and descriptions of organisms

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

    Botanical families

    np_acts-logits-general · gemini-2.0-flash

    biological family names

    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
    matchCondition
    -0.47
    localPosition
    -0.46
    出版年
    -0.45
    paramref
    -0.45
     culturel
    -0.44
    Segoe
    -0.43
    LEncoder
    -0.42
    jsonwebtoken
    -0.42
    BuildContext
    -0.42
    hnia
    -0.42
    POSITIVE LOGITS
     family
    1.26
    Family
    1.17
     Family
    1.15
    family
    1.14
     FAMILY
    1.11
     familie
    1.05
     famiglia
    1.04
     famille
    1.01
    FAMILY
    1.00
     familia
    1.00
    Activations Density 0.434%

    No Known Activations