© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35003
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to positioning and arrangement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    movement behind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viungo
    -0.37
    InstrumentedTest
    -0.34
    Šaltiniai
    -0.33
     验证
    -0.32
    Hints
    -0.32
     วัด
    -0.32
    Cyfarwyddwr
    -0.32
     Marion
    -0.31
     Art
    -0.31
    bauen
    -0.31
    POSITIVE LOGITS
     للمعارف
    0.59
     createSprite
    0.56
     convoy
    0.56
     zuſammen
    0.51
     convo
    0.51
     geſch
    0.51
     follower
    0.49
     referrerpolicy
    0.49
     SLOW
    0.49
    </tfoot>
    0.48
    Activations Density 0.036%

    No Known Activations