© 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. 930
    Prev
    Next
    INDEX
    Explanations

    the word "almost" in various contexts

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

    Followed by words indicating certainty or universality

    np_acts-logits-general · gemini-2.0-flash

    Almost + (all/everyone/everything/certainly/never)

    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
    SBATCH
    -0.62
     विश्वसनीयता
    -0.61
    بوابة
    -0.56
     Meksiku
    -0.56
     وتسجيلات
    -0.56
    either
    -0.56
     cref
    -0.53
    IContainer
    -0.51
     <=",
    -0.51
     muitas
    -0.51
    POSITIVE LOGITS
     identical
    0.84
     exclusively
    0.81
     entirely
    0.79
     imperceptible
    0.78
     impossible
    0.76
     certainly
    0.73
     universally
    0.73
     instantaneously
    0.73
     indistingu
    0.72
     Iden
    0.72
    Activations Density 0.127%

    No Known Activations