© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 7333
    Prev
    Next
    INDEX
    Explanations

    conversational and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spect
    -0.36
    żesz
    -0.34
    SUBMIT
    -0.31
     Submit
    -0.29
     Submissions
    -0.29
    verwijspagina
    -0.29
    makedirs
    -0.29
    afficheront
    -0.29
    subscribers
    -0.28
    INTEGR
    -0.28
    POSITIVE LOGITS
     conversation
    1.17
     conversations
    1.04
     discussion
    1.04
     conversación
    1.01
     discussions
    0.96
     conversational
    0.94
     talk
    0.94
    conversation
    0.91
    Conversation
    0.89
     discuss
    0.89
    Activations Density 0.432%

    No Known Activations