© 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. 21-GEMMASCOPE-RES-16K
    11. 2972
    Prev
    Next
    INDEX
    Explanations

    patterns in programming syntax, particularly related to conditional statements and 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
    ($__
    -0.82
    RenderAtEndOf
    -0.75
    WireFormatLite
    -0.70
     ujednoznacz
    -0.69
    LookAnd
    -0.69
    ngrx
    -0.67
    MergeFrom
    -0.66
    存于互联网档案馆
    -0.66
    }{*}{
    -0.64
    屓
    -0.62
    POSITIVE LOGITS
     there
    0.53
     we
    0.51
     it
    0.47
    __":
    0.46
    __':
    0.45
    ,
    0.44
     they
    0.43
     NSCoder
    0.39
     pertanto
    0.36
    there
    0.35
    Activations Density 0.122%

    No Known Activations