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. 21-GEMMASCOPE-RES-16K
    6. 599
    Prev
    Next
    INDEX
    Explanations

    attribute-value pairs typically found in HTML or XML elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XH
    -0.63
     onView
    -0.57
     SOS
    -0.56
     Milne
    -0.56
    instancetype
    -0.56
    ますね
    -0.54
    ).
    -0.52
     wireType
    -0.52
    SOS
    -0.51
     Util
    -0.50
    POSITIVE LOGITS
    ="
    0.79
    ='
    0.62
    ={
    0.59
    oredCriteria
    0.52
    PathVariable
    0.51
     femininos
    0.50
    ]="
    0.48
    তথ্যসূত্র
    0.47
    ="_
    0.47
     ویکی‌پدیای
    0.47
    Activations Density 0.160%

    No Known Activations