Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 5150
    Prev
    Next
    INDEX
    Explanations

    the word "zur" and its variations in context

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

    thereto and ddot

    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
     дописавши
    -0.59
    schon
    -0.59
    ckså
    -0.57
     fubject
    -0.57
    Schon
    -0.52
     Bagdad
    -0.51
     Spitze
    -0.51
    東西
    -0.51
     Mendez
    -0.50
    anskje
    -0.49
    POSITIVE LOGITS
     zur
    1.72
     Zur
    1.32
    Zur
    1.23
    zur
    1.09
    verwijspagina
    0.54
     alcuna
    0.53
     surla
    0.46
     ensure
    0.46
     כדי
    0.45
     alcun
    0.44
    Activations Density 0.002%

    No Known Activations