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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 12109
    Prev
    Next
    INDEX
    Explanations

    technical specifications relating to document formatting and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    expandindo
    -0.88
    IUrlHelper
    -0.85
    parsedMessage
    -0.81
     queſta
    -0.72
     Infórmanos
    -0.71
    QMetaType
    -0.69
    WithIOException
    -0.68
    PreferredItem
    -0.67
     transfieras
    -0.65
    хьтан
    -0.65
    POSITIVE LOGITS
    textwidth
    0.60
     completos
    0.42
     completas
    0.39
     Schulter
    0.37
     completo
    0.35
    resco
    0.35
     uwagi
    0.34
     Atenas
    0.34
     Atem
    0.34
     full
    0.34
    Activations Density 0.070%

    No Known Activations