© 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. 10-GEMMASCOPE-RES-16K
    11. 16040
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.33
     chromos
    -0.31
     HttpStatusCode
    -0.30
    makeText
    -0.30
    NaOH
    -0.30
    WithIOException
    -0.29
     tiempo
    -0.29
     hambre
    -0.29
    Personensuche
    -0.29
    strongly
    -0.29
    POSITIVE LOGITS
     except
    1.39
     Except
    1.37
    Except
    1.34
    except
    1.34
     kecuali
    1.10
     excepto
    1.08
     excepting
    1.03
     sauf
    0.99
     außer
    0.99
     EXCEPT
    0.99
    Activations Density 0.235%

    No Known Activations