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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 22367
    Prev
    Next
    INDEX
    Explanations

    references to academic article citations and links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     الاطلاع
    -0.55
     autorytatywna
    -0.47
    Personendaten
    -0.46
     Meksiku
    -0.43
    탤
    -0.39
    }$​
    -0.38
    uxxxx
    -0.37
    utilisons
    -0.36
     ivelany
    -0.35
    ]=>
    -0.35
    POSITIVE LOGITS
     vectorielle
    0.54
     urbain
    0.47
    VersionUID
    0.47
     AssemblyCompany
    0.45
     Rowan
    0.45
     okuyayım
    0.44
    ModelSerializer
    0.44
     Tanto
    0.44
     humanas
    0.43
    Jîn
    0.43
    Activations Density 0.075%

    No Known Activations