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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 33-GEMMASCOPE-RES-131K
    6. 65870
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax or methods in JavaScript

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.93
    niſſe
    -0.86
    SequentialGroup
    -0.82
    HtmlAttribute
    -0.82
    ſehen
    -0.81
    SourceChecksum
    -0.80
     tartalomajánló
    -0.80
    iſchen
    -0.79
    ſicht
    -0.78
    <pad>
    -0.75
    POSITIVE LOGITS
     dimaksud
    0.50
     keseluruhan
    0.48
     mevcut
    0.48
     sebaliknya
    0.47
     allgemeine
    0.47
     Öffnungszeiten
    0.47
     Geschichts
    0.45
     individuales
    0.44
     auriculares
    0.43
     persönliche
    0.42
    Activations Density 0.057%

    No Known Activations