© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14783
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and transactions, particularly those related to engineering and data analysis

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

    academic citation information in scholarly publications, especially journal names and bibliographic details.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    strijden
    -0.43
    )="
    -0.42
     CTA
    -0.41
     MPR
    -0.41
    <&
    -0.41
     Æ
    -0.40
     exoner
    -0.40
     referrerpolicy
    -0.40
    elry
    -0.40
     Prä
    -0.39
    POSITIVE LOGITS
     Grecs
    0.52
     IEEE
    0.49
     CreateTagHelper
    0.48
     Exactos
    0.48
    IEEE
    0.47
     propOrder
    0.46
     génie
    0.45
     Schichten
    0.45
     Dichter
    0.45
     Infór
    0.45
    Activations Density 0.248%

    No Known Activations