© 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. 0-GEMMASCOPE-RES-16K
    11. 14886
    Prev
    Next
    INDEX
    Explanations

    programming-related commands or keywords, particularly those associated with deletion or removal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DialogResult
    -0.43
    <bos>
    -0.41
    setattr
    -0.41
    znál
    -0.38
     sourire
    -0.36
     >=",
    -0.34
     issue
    -0.32
     arbre
    -0.31
     rū
    -0.31
    Bibliograf
    -0.31
    POSITIVE LOGITS
    transQ
    0.63
     copy
    0.59
     scratch
    0.58
     spam
    0.56
     Dust
    0.54
    BeginInit
    0.54
     DI
    0.54
    CppMethod
    0.54
    pyx
    0.53
     dusting
    0.53
    Activations Density 0.239%

    No Known Activations