Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3399
    Prev
    Next
    INDEX
    Explanations

    alphanumeric strings, specifically identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     présidentielle
    -0.52
     itſelf
    -0.45
     presidencial
    -0.44
     présidenti
    -0.44
     voulait
    -0.44
    ſelf
    -0.43
     auroit
    -0.42
    énéral
    -0.41
     dentaire
    -0.41
     faſt
    -0.40
    POSITIVE LOGITS
    expandindo
    0.76
    uxxxx
    0.68
    endregion
    0.54
    UnsafeEnabled
    0.51
     betweenstory
    0.50
     CanadaChoose
    0.46
     AssemblyProduct
    0.45
    enterOuterAlt
    0.43
    存于互联网档案馆
    0.43
    يكب
    0.42
    Activations Density 0.095%

    No Known Activations