© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 1108
    Prev
    Next
    INDEX
    Explanations

    code defining macros or functions, particularly those involving bitwise operations and type definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.58
     myſelf
    -0.55
     poffible
    -0.51
     ſeveral
    -0.47
     ſta
    -0.46
     houſe
    -0.45
     étoit
    -0.44
     ſche
    -0.44
     poffe
    -0.43
    kmäler
    -0.42
    POSITIVE LOGITS
    UserScript
    0.63
     CanadaChoose
    0.54
    
    0.52
     وتسجيلات
    0.51
    postIndex
    0.51
     كومونز
    0.50
    xodo
    0.50
    GenerationType
    0.50
     autorytatywna
    0.49
    ClientRect
    0.49
    Activations Density 0.887%

    No Known Activations