© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12165
    Prev
    Next
    INDEX
    Explanations

    information related to scientific research and medical studies

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

    preceding prepositions

    np_acts-logits-general · gemini-2.0-flash

    concepts and situations

    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
    NUMX
    -0.93
    ^(@)
    -0.82
     houſe
    -0.76
     Efq
    -0.76
    ='';
    -0.71
     purpoſe
    -0.71
    .}~\
    -0.71
    )}</
    -0.71
    */].
    -0.70
     ſmall
    -0.70
    POSITIVE LOGITS
     During
    1.11
     Through
    1.07
     Before
    1.04
     Between
    1.02
     Throughout
    1.02
     Without
    1.01
     Within
    0.98
     That
    0.97
     Against
    0.97
     With
    0.94
    Activations Density 0.422%

    No Known Activations