© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 939
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming functions, particularly in Java and PHP

    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
     :-(
    -0.47
     IMHO
    -0.45
     ;-)
    -0.44
    )».
    -0.44
     معظم
    -0.42
     …)
    -0.41
     auroit
    -0.41
    licherweise
    -0.41
    ;-)
    -0.40
     IIRC
    -0.40
    POSITIVE LOGITS
     variable
    0.60
     array
    0.60
    awtextra
    0.60
    enderror
    0.59
     string
    0.54
     value
    0.54
     arrayList
    0.54
     variabel
    0.53
     corrispond
    0.52
     corris
    0.51
    Activations Density 1.187%

    No Known Activations