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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1516
    Prev
    Next
    INDEX
    Explanations

    references to significant events or actions in history, particularly those related to legislation and media developments

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

    following prepositions

    np_acts-logits-general · gemini-2.0-flash

    to study film or did film

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    endphp
    -0.50
    ✭✭
    -0.44
    تقاوى
    -0.43
    хьтан
    -0.41
     gela
    -0.39
    WEBPACK
    -0.38
     صوتيه
    -0.36
    thâu
    -0.36
    gusting
    -0.36
    deleteById
    -0.35
    POSITIVE LOGITS
    ंदीखरीदारी
    0.56
    httphttps
    0.48
    WaitGroup
    0.47
    Erreferentziak
    0.46
    izr
    0.44
    Examples
    0.44
    DoubleQuotes
    0.43
     examples
    0.43
     للمعارف
    0.42
     Fälle
    0.41
    Activations Density 0.508%

    No Known Activations