© 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. 21-GEMMASCOPE-RES-16K
    11. 12003
    Prev
    Next
    INDEX
    Explanations

    references to significant places, events, or conditions related to art, culture, or historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -1.12
    Rüyada
    -0.74
     insuffisamment
    -0.67
     للمعارف
    -0.64
    gonic
    -0.59
    Erstellt
    -0.58
     autorytatywna
    -0.57
    SPATH
    -0.56
    newswire
    -0.56
    ClassNotFound
    -0.55
    POSITIVE LOGITS
    getDescriptor
    0.53
    MigrationBuilder
    0.50
     Antarctica
    0.47
     auditorium
    0.47
     procur
    0.46
    znego
    0.45
    AttributeSet
    0.45
     Batalla
    0.45
     Sealed
    0.45
     Mutant
    0.43
    Activations Density 0.054%

    No Known Activations