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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7055
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    ợt
    -0.59
    fag
    -0.53
    ]))
    
    -0.53
    writeFieldEnd
    -0.52
    acheteur
    -0.52
     weihnachten
    -0.51
    )))
    
    -0.51
     herewith
    -0.50
     Perſ
    -0.50
     beginnetje
    -0.49
    POSITIVE LOGITS
    meta
    0.68
    
    0.66
    httphttps
    0.59
     Meta
    0.56
    SBATCH
    0.55
    rungsseite
    0.54
    водства
    0.54
     linkovi
    0.53
     meta
    0.52
    Diweddarwch
    0.51
    Activations Density 0.082%

    No Known Activations