© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14456
    Prev
    Next
    INDEX
    Explanations

    statements and questions related to beliefs and opinions

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

    Follows discourse markers or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    And with certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    깥
    -0.78
     ddelweddau
    -0.68
    ]}"
    -0.68
     undersigned
    -0.68
     Roskov
    -0.66
    Such
    -0.65
     !)
    -0.65
     Pois
    -0.63
    )="
    -0.63
     Such
    -0.62
    POSITIVE LOGITS
     obviously
    1.10
     certainly
    1.02
    obviously
    0.93
     oftentimes
    0.92
    certainly
    0.91
     particularly
    0.88
     basically
    0.86
     everybody
    0.85
     essentially
    0.85
     effectivement
    0.84
    Activations Density 0.177%

    No Known Activations