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. 568
    Prev
    Next
    INDEX
    Explanations

    medical and diagnostic terminology related to health conditions

    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
     autorytatywna
    -0.66
    Autoritní
    -0.44
    citenamefont
    -0.43
    országban
    -0.42
    });
    
    
    -0.40
     Coloring
    -0.39
    ServletException
    -0.39
     PeEnEo
    -0.39
    untura
    -0.38
    NamedQueries
    -0.38
    POSITIVE LOGITS
     indicate
    0.51
     signify
    0.47
     indicating
    0.45
     signifies
    0.44
    indic
    0.44
     indicative
    0.44
     indicates
    0.43
     Italijani
    0.43
     témo
    0.43
     signals
    0.42
    Activations Density 0.675%

    No Known Activations