© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14716
    Prev
    Next
    INDEX
    Explanations

    verbs associated with speaking and communication

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

    "speak" or "spoke"

    np_acts-logits-general · gemini-2.0-flash

    speak about or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ddots
    -0.59
    DialogTitle
    -0.59
    OGND
    -0.57
    ⓧ
    -0.54
     Walkover
    -0.54
    oraz
    -0.53
    bootstrapcdn
    -0.51
    medies
    -0.51
    unknownFields
    -0.51
    photobucket
    -0.49
    POSITIVE LOGITS
     volumes
    1.00
     Volumes
    0.83
    volumes
    0.75
     fluent
    0.73
     louder
    0.72
     truth
    0.72
    Volumes
    0.72
     chiaro
    0.68
     about
    0.66
     highly
    0.64
    Activations Density 0.059%

    No Known Activations