© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9391
    Prev
    Next
    INDEX
    Explanations

    the word "tu" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kn
    -0.56
     vul
    -0.52
    ioutil
    -0.49
     Quir
    -0.49
     kent
    -0.48
     Kno
    -0.47
     poly
    -0.47
     ô
    -0.46
     Trump
    -0.46
    MUR
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.58
     snaps
    0.54
     snap
    0.54
     snapping
    0.54
     snapped
    0.51
    ת
    0.50
    utuhkan
    0.49
    snap
    0.49
    цездатний
    0.49
    Tu
    0.49
    Activations Density 0.274%

    No Known Activations