© 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. 22-GEMMASCOPE-RES-16K
    11. 7054
    Prev
    Next
    INDEX
    Explanations

    narrative elements related to stories and their impact

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

    "... in part" or "a part"

    np_acts-logits-general · gemini-2.0-flash

    in part to

    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
     Roskov
    -1.11
    Демографія
    -0.78
     MainAxisSize
    -0.77
    клопе
    -0.73
    StoryboardSegue
    -0.73
    setVerticalGroup
    -0.72
     Мексичка
    -0.71
    Попис
    -0.70
    ScopeManager
    -0.68
    География
    -0.68
    POSITIVE LOGITS
     part
    4.47
    part
    3.93
    Part
    3.59
     Part
    3.37
     parte
    3.27
     parts
    3.01
     PART
    2.99
    PART
    2.67
     Teil
    2.63
    parts
    2.59
    Activations Density 0.944%

    No Known Activations