© 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. 34-GEMMASCOPE-RES-16K
    11. 11528
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and constructs, particularly in Java and potentially other programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     again
    -0.49
     Abbott
    -0.48
     AB
    -0.48
     Adams
    -0.48
     ab
    -0.47
     Ab
    -0.46
     Abs
    -0.45
     Alabama
    -0.45
     Again
    -0.44
     Abraham
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    0.73
    Cyfarwyddwr
    0.64
    Datuak
    0.63
     nahilalakip
    0.62
    ніципалі
    0.62
    ⪜
    0.60
    outWeight
    0.60
     doInBackground
    0.59
     Paglinawan
    0.59
     ProtoMessage
    0.59
    Activations Density 0.202%

    No Known Activations