Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7910
    Prev
    Next
    INDEX
    Explanations

    color codes and formatting specifications in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hexadecimal color codes

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal colors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apimachinery
    -0.68
    )]
    
    -0.67
    ,))
    -0.66
    '])
    
    -0.66
     BoxFit
    -0.65
    ]]
    
    -0.64
    Kaynakça
    -0.64
    "])
    
    -0.63
    )";
    
    -0.63
    ).]
    -0.62
    POSITIVE LOGITS
    fff
    0.55
    ffffff
    0.52
    cccccc
    0.51
     Corbu
    0.48
     communism
    0.46
    ccc
    0.45
     Tenta
    0.45
     democracy
    0.43
     Transc
    0.43
     néer
    0.43
    Activations Density 0.087%

    No Known Activations