© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 5003
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to mythology and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.92
     يتيمه
    -0.87
    PickerController
    -0.81
     GNA
    -0.76
    ICom
    -0.73
     wanda
    -0.72
    aio
    -0.72
    躇
    -0.72
     Koro
    -0.72
    gonic
    -0.71
    POSITIVE LOGITS
     Huf
    1.09
     Haf
    1.05
     Sif
    1.05
    Coff
    0.99
     Kaf
    0.97
     HIF
    0.97
    uf
    0.95
     waf
    0.94
     yf
    0.94
    idf
    0.92
    Activations Density 1.598%

    No Known Activations