© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 9649
    Prev
    Next
    INDEX
    Explanations

    instances of active listening and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.96
     geladeira
    -0.84
    DotNetBar
    -0.82
     vloer
    -0.80
     piú
    -0.80
     Farrar
    -0.77
     devrez
    -0.77
    OCCURRED
    -0.77
     sostanze
    -0.76
     egli
    -0.76
    POSITIVE LOGITS
     listen
    1.75
     LISTEN
    1.69
     listening
    1.66
     Listen
    1.63
     listens
    1.59
     listened
    1.58
     Listening
    1.56
    Listen
    1.50
    Listening
    1.45
    listen
    1.36
    Activations Density 0.026%

    No Known Activations