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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-131K
    6. 103357
    Prev
    Next
    INDEX
    Explanations

    characters representing data types or syntax in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    special characters and french words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.65
    WEBPACK
    -0.61
    printStackTrace
    -0.55
     Urqu
    -0.54
                                   
    -0.52
     Stol
    -0.51
     Colla
    -0.51
     Grimal
    -0.51
    collate
    -0.51
     Giovan
    -0.50
    POSITIVE LOGITS
     Inscrivez
    0.52
     ennemi
    0.51
     fidé
    0.49
     Partager
    0.47
     étranger
    0.46
     eût
    0.46
    
    0.46
     Voyez
    0.45
     defaultstate
    0.44
    麼
    0.44
    Activations Density 0.147%

    No Known Activations