© 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. 8307
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate certainty or obviousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    adaptiveStyles
    -0.53
    Autoritní
    -0.49
     @"/
    -0.45
     sento
    -0.45
    CreateModel
    -0.44
    SharedCtor
    -0.41
    Похо
    -0.41
     resourceCulture
    -0.40
     ligiloj
    -0.39
    ThroughAttribute
    -0.39
    POSITIVE LOGITS
     natürlich
    0.96
    Obviously
    0.92
     obviously
    0.92
    obviously
    0.92
     natuurlijk
    0.90
    eraard
    0.90
     Obviously
    0.89
    verständlich
    0.87
     Natürlich
    0.85
     obviamente
    0.84
    Activations Density 0.129%

    No Known Activations