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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8024
    Prev
    Next
    INDEX
    Explanations

    interactions involving specific individuals and actions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sequences describing someone arriving or showing up at a location to help or interact with another person.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ліст
    -0.40
    centration
    -0.39
    campista
    -0.36
     kän
    -0.35
     متعلقه
    -0.35
    imanapun
    -0.34
     exportaciones
    -0.34
     moneda
    -0.34
    JsonInclude
    -0.34
    TagMode
    -0.34
    POSITIVE LOGITS
     come
    1.78
     datang
    1.69
     coming
    1.68
     came
    1.66
     arrive
    1.64
     arrives
    1.63
     comes
    1.60
     COME
    1.54
     arrived
    1.50
    Come
    1.49
    Activations Density 0.572%

    No Known Activations