© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5835
    Prev
    Next
    INDEX
    Explanations

    expressions and phrases related to listening and communication dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    listening or believing

    np_acts-logits-general · gemini-2.0-flash

    listen and take advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wireType
    -0.42
     desempeño
    -0.36
     springfox
    -0.36
    omeness
    -0.36
     performance
    -0.36
     découver
    -0.35
    PERFORMANCE
    -0.35
     declarar
    -0.34
     occasion
    -0.34
     PERFORMANCE
    -0.34
    POSITIVE LOGITS
     listened
    1.12
     listen
    1.02
     listens
    0.93
     listening
    0.90
     heed
    0.88
     écout
    0.87
    listen
    0.87
     Listen
    0.82
     LISTEN
    0.81
    Listen
    0.79
    Activations Density 0.391%

    No Known Activations