© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6125
    Prev
    Next
    INDEX
    Explanations

    evaluative language and expressions of comparison

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

    Followed by an intensifier

    np_acts-logits-general · gemini-2.0-flash

    like spectacular

    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
     /\.(
    -0.57
     esimerkiksi
    -0.53
    étaire
    -0.51
     примеру
    -0.51
     bijvoorbeeld
    -0.50
     Ceramby
    -0.49
     betrekking
    -0.49
    例文帳に追加
    -0.48
     zvuky
    -0.48
    mleri
    -0.47
    POSITIVE LOGITS
     pure
    1.03
     déjà
    0.84
     overkill
    0.83
     deja
    0.80
    pure
    0.75
     Pure
    0.74
     pura
    0.73
     wishful
    0.73
     sheer
    0.71
    Pure
    0.70
    Activations Density 0.309%

    No Known Activations