© 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. 21-GEMMASCOPE-RES-16K
    11. 13422
    Prev
    Next
    INDEX
    Explanations

    conversational indicators and responses in a dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enjeux
    -0.45
     arşivlendi
    -0.44
     remplissage
    -0.43
     tunn
    -0.41
     Vordergrund
    -0.41
    MEMORY
    -0.40
     verdaderamente
    -0.39
     snippetHide
    -0.39
    Interes
    -0.39
     continuidad
    -0.39
    POSITIVE LOGITS
     answer
    0.56
    answer
    0.54
     answers
    0.51
    ValueStyle
    0.46
     Answer
    0.46
     Exacts
    0.44
     yes
    0.43
    answers
    0.42
    回答
    0.42
     antwoord
    0.42
    Activations Density 0.327%

    No Known Activations