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. 6037
    Prev
    Next
    INDEX
    Explanations

    contextual information related to mechanical components and their functions

    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
     vectorielle
    -0.37
     davor
    -0.35
    oa̍t
    -0.35
    olisme
    -0.34
     libéral
    -0.33
     pertin
    -0.33
    gans
    -0.33
     leven
    -0.33
     sectional
    -0.32
     Perusahaan
    -0.32
    POSITIVE LOGITS
     ujednoznacz
    0.65
    WireFormatLite
    0.59
     nahilalakip
    0.57
     ब्रेकडाउन
    0.55
    GEBURTS
    0.48
    IsContent
    0.48
     виправивши
    0.46
    WriteTagHelper
    0.46
    ########.
    0.46
    
    0.46
    Activations Density 0.524%

    No Known Activations