© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9958
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal satisfaction and positive experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     semblable
    -0.30
     often
    -0.29
     bordo
    -0.29
     strane
    -0.28
    šča
    -0.28
     scom
    -0.28
    boven
    -0.27
     parezca
    -0.26
     بالق
    -0.26
    DIPSETTING
    -0.26
    POSITIVE LOGITS
    utilisons
    0.68
     Normdatei
    0.66
    OGND
    0.63
    uxxxx
    0.56
    PyExc
    0.55
    تفصیلات
    0.55
     BoxFit
    0.54
    verifyException
    0.54
     HasFactory
    0.54
    
    0.54
    Activations Density 0.073%

    No Known Activations