© 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. 37-GEMMASCOPE-RES-16K
    11. 1534
    Prev
    Next
    INDEX
    Explanations

    characters or people that thrive in social situations and enjoy interacting with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.53
    +#+#
    -0.51
    таратура
    -0.47
    HtmlAttribute
    -0.46
     Inscrivez
    -0.44
     ProtoMessage
    -0.43
    发表于
    -0.42
    #+#
    -0.40
     HasFactory
    -0.40
    帖最后由
    -0.40
    POSITIVE LOGITS
     interact
    1.23
     interacts
    1.13
     interacting
    1.13
     interacted
    1.13
     interag
    0.99
    interact
    0.98
     interaction
    0.95
     socialize
    0.95
     Interact
    0.92
     interactions
    0.90
    Activations Density 0.519%

    No Known Activations