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 - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 140
    Prev
    Next
    INDEX
    Explanations

    coding-related syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pungkas
    -0.56
     spørgsmål
    -0.52
    transQ
    -0.52
     förslag
    -0.52
     almohada
    -0.50
     mukaan
    -0.50
     beleid
    -0.50
     persoalan
    -0.49
     pungkasnya
    -0.48
     pidana
    -0.48
    POSITIVE LOGITS
    >{@
    0.64
    IsContent
    0.63
    ]")]
    0.57
    '][$
    0.53
    %")
    0.52
     AssemblyProduct
    0.51
    ($__
    0.50
    __*/
    0.50
    "),
    
    0.49
     aload
    0.49
    Activations Density 1.219%

    No Known Activations