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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12454
    Prev
    Next
    INDEX
    Explanations

    instances of quotation marks or speech representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intval
    -0.47
     setContent
    -0.47
    Zah
    -0.47
    »»
    -0.46
     arom
    -0.45
     mData
    -0.44
    ...»
    -0.44
    "
    -0.43
     balan
    -0.43
     sendMessage
    -0.43
    POSITIVE LOGITS
     ‘
    0.83
     '
    0.65
     (‘
    0.55
     Schülerinnen
    0.52
     delgada
    0.49
    (‘
    0.49
     ’
    0.48
     Audiodateien
    0.48
     sintética
    0.48
     convocatoria
    0.48
    Activations Density 0.221%

    No Known Activations