© 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. 2-GEMMASCOPE-RES-16K
    11. 9422
    Prev
    Next
    INDEX
    Explanations

    the word "drawing" and variations of the word "guess" along with the word "ou."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.55
    קישורים
    -0.52
     StringTokenizer
    -0.51
    Enllaços
    -0.50
    StoryboardSegue
    -0.50
     useAppContext
    -0.49
    Spoljašnje
    -0.46
     мәгълү
    -0.45
    Bronnen
    -0.45
    Šaltiniai
    -0.45
    POSITIVE LOGITS
    у
    1.40
    У
    1.16
     у
    1.03
     У
    0.97
    уд
    0.52
    Drawing
    0.52
    过
    0.51
    過
    0.51
     ou
    0.51
     ў
    0.50
    Activations Density 0.039%

    No Known Activations