© 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. 7747
    Prev
    Next
    INDEX
    Explanations

    references to various concepts of "way" or "ways"

    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
    __*/
    -0.68
    ंदीखरीदारी
    -0.60
    хьтан
    -0.52
    __":
    -0.52
    principalTable
    -0.52
     uuidv
    -0.51
     DbSet
    -0.50
    astify
    -0.49
    SequentialGroup
    -0.49
    AddHtmlAttribute
    -0.49
    POSITIVE LOGITS
     WAY
    0.66
    Way
    0.63
    farer
    0.60
    faring
    0.59
     Way
    0.59
    farers
    0.59
     way
    0.56
    way
    0.55
    fare
    0.53
    side
    0.51
    Activations Density 0.112%

    No Known Activations