© 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. 18-GEMMASCOPE-RES-16K
    11. 9900
    Prev
    Next
    INDEX
    Explanations

    expressions of degree or extent, particularly involving the word "too"

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

    Follows "too" or "so" and modifies an adjective

    np_acts-logits-general · gemini-2.0-flash

    not too much

    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
     virtually
    -0.52
    hak
    -0.48
     almost
    -0.47
    rice
    -0.43
     ra
    -0.43
    almost
    -0.42
    cep
    -0.41
    GIVEREF
    -0.39
    vir
    -0.39
    tometer
    -0.37
    POSITIVE LOGITS
     tampoco
    0.93
     anymore
    0.89
    enumi
    0.87
     Tampoco
    0.87
     nemmeno
    0.84
    IntoConstraints
    0.84
     Monfieur
    0.84
    rrggbb
    0.80
     siquiera
    0.80
     lắm
    0.79
    Activations Density 0.129%

    No Known Activations