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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5261
    Prev
    Next
    INDEX
    Explanations

    class and method declarations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    курен
    -0.54
    уза
    -0.51
     виправивши
    -0.50
    __':
    
    -0.50
    onaceous
    -0.50
    glMatrixMode
    -0.48
     afer
    -0.47
     people
    -0.47
     ucha
    -0.47
    .*")]
    -0.46
    POSITIVE LOGITS
     defStyleAttr
    0.73
    dafx
    0.67
    :✨
    0.66
     Réponses
    0.64
    ########.
    0.64
    */].
    0.60
    はじめに
    0.57
     UnityEditor
    0.57
    Xna
    0.57
    orszá
    0.56
    Activations Density 3.159%

    No Known Activations