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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 7068
    Prev
    Next
    INDEX
    Explanations

    URLs and references to online resources or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     säll
    -0.31
     purpoſe
    -0.27
     bolsillos
    -0.27
     personnelles
    -0.26
     personal
    -0.25
     hardly
    -0.25
     rarely
    -0.24
     cardíaca
    -0.23
     however
    -0.23
     meaning
    -0.23
    POSITIVE LOGITS
    enumii
    0.81
    RegressionTest
    0.78
    enumi
    0.71
    sizeCache
    0.69
    fromnode
    0.66
     intptr
    0.66
    +#+
    0.62
    VersionUID
    0.62
    ItemBackground
    0.61
     betweenstory
    0.60
    Activations Density 1.373%

    No Known Activations