© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1008
    Prev
    Next
    INDEX
    Explanations

    references to actions and verbs associated with choice, travel, and instructions

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

    Following "to"

    np_acts-logits-general · gemini-2.0-flash

    verbs indicating purpose

    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
    CodedInputStream
    -0.57
    --)
    -0.55
    Reach
    -0.53
    ρίς
    -0.51
    hdashline
    -0.50
    tomation
    -0.49
    ')")
    -0.48
    arsk
    -0.48
    ╮
    -0.47
    eddah
    -0.46
    POSITIVE LOGITS
     ajudá
    0.74
    用来
    0.72
     help
    0.71
     complement
    0.69
     compliment
    0.63
    TypedDataSet
    0.63
    jooq
    0.62
     مرئيه
    0.62
     للمعارف
    0.62
    +#+#
    0.62
    Activations Density 0.166%

    No Known Activations