© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 15953
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...
    -0.81
    …
    -0.75
    “
    -0.75
    ,
    -0.73
    「
    -0.69
    /
    -0.62
    -
    -0.61
    .
    -0.61
    "
    -0.60
    :
    -0.58
    POSITIVE LOGITS
     czyli
    1.20
     valamint
    1.11
     etc
    1.11
     iaitu
    1.09
     illetve
    1.09
     albeit
    1.04
     yaitu
    1.02
     nonché
    1.02
     yakni
    1.01
     ovvero
    1.00
    Activations Density 2.709%

    No Known Activations