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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5810
    Prev
    Next
    INDEX
    Explanations

    structured mathematical notation or labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.54
    PMailer
    -0.53
    ]")]
    -0.52
     aank
    -0.50
    Jeografia
    -0.50
    новниш
    -0.49
     otomatig
    -0.49
     autorytatywna
    -0.49
    PreInfinity
    -0.48
    cèse
    -0.48
    POSITIVE LOGITS
     informée
    0.36
     Allociné
    0.34
     tartalomajánló
    0.29
     חיצוניים
    0.29
    AccessorTable
    0.29
     oliva
    0.28
    LLocation
    0.27
     plonge
    0.27
    semibold
    0.26
     nela
    0.26
    Activations Density 0.112%

    No Known Activations