© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2477
    Prev
    Next
    INDEX
    Explanations

    specific file types or formatted data

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

    scientific and medical research terminology, particularly related to laboratory testing and experimental methods.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.90
    AutoScaleMode
    -0.78
    tagHelperRunner
    -0.76
     TestBed
    -0.74
     Administrativna
    -0.73
     <>",
    -0.71
    
    -0.71
    DockStyle
    -0.69
    RectangleBorder
    -0.69
     ſeine
    -0.68
    POSITIVE LOGITS
     выде
    0.29
     Tiene
    0.28
    mesine
    0.26
     Catch
    0.26
     húmedo
    0.25
    上
    0.25
     Estad
    0.25
     Hairst
    0.25
     Relaciones
    0.24
     alarg
    0.24
    Activations Density 0.217%

    No Known Activations