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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4832
    Prev
    Next
    INDEX
    Explanations

    code snippets and syntax elements in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.56
     getItemCount
    -0.50
     utafitiHapana
    -0.49
    makeConstraints
    -0.47
     ویکی‌پدی
    -0.47
    MLLoader
    -0.47
    
    -0.47
     AssemblyVersion
    -0.46
    BagConstraints
    -0.45
     autorytatywna
    -0.45
    POSITIVE LOGITS
     INTERESAR
    0.44
    ']?>
    0.42
     aDecoder
    0.41
    .*")]
    0.38
    ";//
    0.36
    ) 
    0.36
    ;");
    0.35
    nieren
    0.34
     }(\
    0.34
    ;";
    0.34
    Activations Density 0.516%

    No Known Activations