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. 12321
    Prev
    Next
    INDEX
    Explanations

    mentions of exceptions or error handling scenarios in the text

    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
    rungsseite
    -0.48
    :✨
    -0.46
    ✷
    -0.46
     trom
    -0.45
     виправивши
    -0.44
    +#+#
    -0.44
     Tanz
    -0.44
     lenker
    -0.44
     diagonal
    -0.44
    膨
    -0.42
    POSITIVE LOGITS
     onCancelled
    0.62
     femininas
    0.56
     muerte
    0.55
     lesión
    0.54
     Infórmanos
    0.54
     médecins
    0.52
    msgTypes
    0.52
     heridos
    0.51
     teorías
    0.50
     zdrowia
    0.50
    Activations Density 0.291%

    No Known Activations