© 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. 14491
    Prev
    Next
    INDEX
    Explanations

    words related to agreement or consensus in statements

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

    preceding exceptions or limitations

    np_acts-logits-general · gemini-2.0-flash

    except

    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
     فريبيس
    -0.60
     EconPapers
    -0.56
     الحره
    -0.56
    onomía
    -0.55
    ronom
    -0.54
     للاسماء
    -0.53
     Савезне
    -0.53
    SequentialGroup
    -0.52
    ganza
    -0.52
     puissiez
    -0.52
    POSITIVE LOGITS
     except
    3.01
    except
    2.70
     Except
    2.37
    Except
    2.35
     EXCEPT
    2.20
     excepto
    2.15
     save
    2.14
     excepting
    2.11
     kecuali
    2.07
     sauf
    2.05
    Activations Density 0.892%

    No Known Activations