© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6988
    Prev
    Next
    INDEX
    Explanations

    references to editions of works, particularly in terms of publications and copies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UVWXYZ
    -0.68
    NOPQRST
    -0.60
    IGraphics
    -0.58
     jadx
    -0.56
    juvant
    -0.55
    [+
    -0.55
    '):
    -0.55
    ISCO
    -0.55
    onnais
    -0.54
     xmlns
    -0.54
    POSITIVE LOGITS
     edition
    1.31
     editions
    1.20
     Edition
    1.05
     édition
    1.02
     version
    1.00
    edition
    0.99
     versions
    0.96
     EDITION
    0.95
     edizione
    0.92
    Edition
    0.91
    Activations Density 0.664%

    No Known Activations