© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9041
    Prev
    Next
    INDEX
    Explanations

    phrases indicating observation or perception, often relating to how something appears or seems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tissa
    -0.63
    Datuak
    -0.58
    neum
    -0.58
    };*/
    -0.56
     aérienne
    -0.56
    ganta
    -0.55
     createSprite
    -0.54
     Bm
    -0.54
     ongles
    -0.53
     hObject
    -0.52
    POSITIVE LOGITS
    Seems
    0.86
     guess
    0.85
    Guess
    0.81
    guess
    0.78
     Guess
    0.77
     Seems
    0.72
     guessing
    0.71
    Looks
    0.69
    看來
    0.69
    看来
    0.68
    Activations Density 0.223%

    No Known Activations