© 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. 8-GEMMASCOPE-RES-16K
    6. 4942
    Prev
    Next
    INDEX
    Explanations

    words that relate to different forms of the root "des."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.98
    ิลปะ
    -0.95
    ReusableCell
    -0.94
    Datuak
    -0.85
     Kidd
    -0.81
    QMetaType
    -0.79
    NameInMap
    -0.79
     MainAxisSize
    -0.78
    Autoritní
    -0.74
    OGND
    -0.74
    POSITIVE LOGITS
     DES
    1.74
     Des
    1.63
    Des
    1.54
    DES
    1.51
     Desai
    1.45
     des
    1.43
    des
    1.40
     Desi
    1.05
    Deserializer
    1.01
     desp
    0.97
    Activations Density 0.135%

    No Known Activations