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. 96527
    Prev
    Next
    INDEX
    Explanations

    details about classic cars and their auctions

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

    muscle car restoration

    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
     CreateTagHelper
    -0.46
    AndroidJUnit
    -0.43
     الرياضيه
    -0.41
    pegno
    -0.41
     createState
    -0.40
     Sheehan
    -0.40
    новништво
    -0.37
    nitus
    -0.37
    rungsseite
    -0.36
     Yamamoto
    -0.36
    POSITIVE LOGITS
     EconPapers
    0.56
     restoration
    0.50
    restore
    0.48
    chieht
    0.48
     intStringLen
    0.47
     restoring
    0.45
    phosa
    0.45
     restore
    0.45
     IBOutlet
    0.44
    QMetaType
    0.43
    Activations Density 0.081%

    No Known Activations