© 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. 24-GEMMASCOPE-RES-16K
    11. 4527
    Prev
    Next
    INDEX
    Explanations

    contradictory or contrasting statements within a sentence

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

    "But"

    np_acts-logits-general · gemini-2.0-flash

    introducing contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irited
    -0.59
    MethodManager
    -0.54
     prolly
    -0.52
    thâu
    -0.52
    ActionCreators
    -0.51
    ніципа
    -0.51
    حياته
    -0.49
    
    -0.49
    ROMA
    -0.49
    ateria
    -0.49
    POSITIVE LOGITS
    expandindo
    0.44
    omock
    0.39
     hvem
    0.38
     But
    0.37
     médié
    0.37
    But
    0.37
    Nevertheless
    0.36
    RenderAtEndOf
    0.35
     fisuras
    0.33
     Nevertheless
    0.33
    Activations Density 0.205%

    No Known Activations