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. 6769
    Prev
    Next
    INDEX
    Explanations

    numeric values and their associated metadata

    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
    Datuak
    -0.57
     BrowserModule
    -0.51
    oa̍t
    -0.47
    ufact
    -0.43
    _${
    -0.42
     שוליים
    -0.41
    bolista
    -0.41
    TagHelper
    -0.41
     FRO
    -0.40
     ویکی‌آمباردا
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    0.55
    complexContent
    0.54
    ValueStyle
    0.49
    NameInMap
    0.42
    GEBURTSDATUM
    0.42
    ByExample
    0.40
    bodyParser
    0.40
    værende
    0.39
     &___
    0.39
    __':
    
    0.39
    Activations Density 0.254%

    No Known Activations