© 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. 20-GEMMASCOPE-RES-16K
    11. 851
    Prev
    Next
    INDEX
    Explanations

    terms related to mollusks and snail shells

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

    Shells and snails

    np_acts-logits-general · gemini-2.0-flash

    snail shells

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.83
    setVerticalGroup
    -0.80
    Filmografie
    -0.73
    harusnya
    -0.72
     betweenstory
    -0.71
    nationality
    -0.68
    loài
    -0.67
    Filmographie
    -0.66
    RectangleBorder
    -0.65
     mosquito
    -0.65
    POSITIVE LOGITS
     shell
    1.54
     Shell
    1.43
     shells
    1.39
    Shell
    1.38
    shell
    1.34
     SHELL
    1.26
     Shells
    1.23
    SHELL
    1.13
    shells
    1.10
     shelled
    0.89
    Activations Density 0.257%

    No Known Activations