Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51866
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to adding, setting, and querying data in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.96
    Personendaten
    -0.79
     ***!
    -0.75
     autorytatywna
    -0.74
    
    -0.72
    XmlAccessType
    -0.71
    Демографія
    -0.71
    Personensuche
    -0.70
     otomatig
    -0.69
     queſta
    -0.69
    POSITIVE LOGITS
    -
    0.47
    _
    0.43
     
    0.42
    ↵↵
    0.42
     primary
    0.39
     top
    0.38
     partial
    0.37
    2
    0.37
     onBind
    0.36
    libft
    0.35
    Activations Density 0.032%

    No Known Activations