© 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. 2-GEMMASCOPE-RES-16K
    11. 8492
    Prev
    Next
    INDEX
    Explanations

    references to speakers and speaking activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.49
     corações
    -0.48
    GOTREF
    -0.48
    Diweddarwch
    -0.47
     खरीदा
    -0.47
     oídos
    -0.45
     convidados
    -0.45
     kupić
    -0.44
     transfieras
    -0.44
     ragaz
    -0.44
    POSITIVE LOGITS
     speaker
    2.30
     speaking
    2.23
     speakers
    2.19
     speak
    2.02
     Speaker
    1.96
     Speakers
    1.95
     Speaking
    1.94
    speaker
    1.94
    speaking
    1.92
    Speaker
    1.83
    Activations Density 0.099%

    No Known Activations