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

    Neuronpedia

    Jacobian LensNEW
    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. 1-GEMMASCOPE-RES-16K
    11. 3754
    Prev
    Next
    INDEX
    Explanations

    mentions of companionship and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Victor
    -0.39
    зу
    -0.34
    fromLTRB
    -0.33
    ο
    -0.33
     exc
    -0.32
    ச்ச
    -0.31
     earth
    -0.30
     newArr
    -0.30
     Lincoln
    -0.30
     “
    -0.30
    POSITIVE LOGITS
     companion
    1.38
     Companion
    1.30
    companion
    1.30
    Companion
    1.24
     accompany
    1.20
     accompanying
    1.16
     accompanies
    1.13
     COMPAN
    1.05
     companions
    1.04
     Begle
    1.01
    Activations Density 0.203%

    No Known Activations