© 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. 24-GEMMASCOPE-RES-16K
    11. 5144
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on" and phrases indicating the presence of specific contexts or situations

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

    "On the" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    introducing a contrasting point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.68
     Meksiku
    -0.68
    ритори
    -0.62
    uxxxx
    -0.61
     Italijani
    -0.56
    ainte
    -0.54
    řevě
    -0.54
     فريبيس
    -0.53
    MessageTagHelper
    -0.51
    unknownFields
    -0.50
    POSITIVE LOGITS
     paper
    0.88
     closer
    0.80
     balance
    0.79
    paper
    0.77
     average
    0.74
     rare
    0.72
    closer
    0.71
     PAPER
    0.71
     contrary
    0.69
    ward
    0.68
    Activations Density 0.109%

    No Known Activations