© 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. 11-GEMMASCOPE-RES-16K
    11. 8317
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest similarity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.47
     מדי
    -0.39
    단
    -0.39
    rás
    -0.38
    MSB
    -0.37
     przedsiębior
    -0.36
    제
    -0.36
    GB
    -0.35
     silo
    -0.35
     katze
    -0.34
    POSITIVE LOGITS
    styleType
    0.72
     CreateTagHelper
    0.64
    twimg
    0.62
     ModelExpression
    0.61
     klingt
    0.60
    afficheront
    0.59
    seemed
    0.59
    ⟬
    0.59
     feels
    0.59
     sounded
    0.59
    Activations Density 0.166%

    No Known Activations