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. 102477
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and molecular weights

    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
     חיצוניים
    -0.55
     OMITBAD
    -0.54
     كومونز
    -0.51
     queſta
    -0.50
     kasarigan
    -0.49
     defaultstate
    -0.49
    IInterface
    -0.47
    IContainer
    -0.47
     glyphicon
    -0.46
     "<?
    -0.45
    POSITIVE LOGITS
     disambiguazione
    0.65
    BeginContext
    0.54
    GOTREF
    0.54
     poids
    0.50
    URIComponent
    0.49
    Viited
    0.46
    weight
    0.45
     weight
    0.45
    kDa
    0.43
     peso
    0.43
    Activations Density 0.037%

    No Known Activations