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. 21-GEMMASCOPE-RES-16K
    6. 5669
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or function calls

    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
    awtextra
    -0.75
    AndEndTag
    -0.72
    rungsseite
    -0.71
     autorytatywna
    -0.71
     CreateTagHelper
    -0.71
     Paglinawan
    -0.65
    NameInMap
    -0.64
    ViewImports
    -0.62
    SourceChecksum
    -0.61
    
    -0.59
    POSITIVE LOGITS
     selections
    0.38
     obligatorio
    0.33
    arium
    0.33
    gde
    0.33
     choices
    0.33
    ënten
    0.32
     Innen
    0.31
     diarios
    0.30
    Tembelea
    0.30
    enteuer
    0.30
    Activations Density 0.143%

    No Known Activations