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. 20-GEMMASCOPE-RES-131K
    6. 53250
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and conjunctions that indicate sentence structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.57
    较为
    -0.52
     Obrador
    -0.52
     Rode
    -0.51
     interacted
    -0.50
    ChildScrollView
    -0.48
    omiast
    -0.47
    bkz
    -0.47
     StatefulWidget
    -0.47
     concerned
    -0.47
    POSITIVE LOGITS
     freakin
    0.50
     fuckin
    0.47
     bastards
    0.45
     crazy
    0.42
     nothin
    0.41
     goddamn
    0.39
     massac
    0.39
    crazy
    0.38
     craz
    0.38
     crap
    0.38
    Activations Density 0.033%

    No Known Activations