Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13854
    Prev
    Next
    INDEX
    Explanations

    anatomical terms and descriptions related to the pharyngeal plexus and surgical procedures

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

    Anatomical terms following "the"

    np_acts-logits-general · gemini-2.0-flash

    anatomical nerves and joints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.88
     betweenstory
    -0.86
     kasarigan
    -0.82
    存于互联网档案馆
    -0.78
     виправивши
    -0.71
     houſe
    -0.69
     ſche
    -0.69
     myſelf
    -0.69
     itſelf
    -0.68
     pleaſure
    -0.68
    POSITIVE LOGITS
     superior
    0.61
     ModelExpression
    0.56
     inferior
    0.55
     poster
    0.54
     processus
    0.53
     auriculares
    0.53
     ant
    0.51
     processi
    0.51
    Poster
    0.51
    superior
    0.50
    Activations Density 0.823%

    No Known Activations