© 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. 35-GEMMASCOPE-RES-16K
    6. 6714
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.45
    хьтан
    -0.44
     оригіналу
    -0.43
    onOptions
    -0.43
    forgotten
    -0.42
    プチ
    -0.41
    atoire
    -0.41
    elbow
    -0.41
     चीज़ों
    -0.41
    原始内容存档于
    -0.40
    POSITIVE LOGITS
        
    0.47
    Aholisi
    0.40
    dill
    0.36
     financeira
    0.36
     Winaray
    0.34
     الرياضيه
    0.34
     francès
    0.34
     étrangères
    0.33
     disambiguazione
    0.33
     alleged
    0.33
    Activations Density 0.225%

    No Known Activations