© 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. 12-GEMMASCOPE-RES-16K__L0-22
    6. 991
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.78
    HtmlAttribute
    -0.60
    Зноскі
    -0.59
    طلحات
    -0.49
     dest
    -0.48
    currentColor
    -0.47
    ветить
    -0.47
    Unmanaged
    -0.46
    houette
    -0.46
    ATUM
    -0.45
    POSITIVE LOGITS
    
    0.76
     knex
    0.68
     NSCoder
    0.63
    StructEnd
    0.59
    NgModule
    0.56
     виправивши
    0.55
    存于互联网档案馆
    0.54
     Drapeau
    0.54
    jalá
    0.53
    Hentet
    0.52
    Activations Density 0.060%

    No Known Activations