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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 8253
    Prev
    Next
    INDEX
    Explanations

    elements related to research methodology and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.56
    PMailer
    -0.54
    ADATA
    -0.49
    djangoproject
    -0.48
     CGSize
    -0.47
     resultCode
    -0.47
    gcf
    -0.47
    :✨
    -0.47
    ]^{-
    -0.46
     initWith
    -0.46
    POSITIVE LOGITS
    mergeFrom
    0.58
     beginnetje
    0.57
     such
    0.56
    such
    0.52
    Such
    0.51
     journaux
    0.51
     Commencement
    0.49
     CHAPITRE
    0.49
     Transcript
    0.48
     Enfin
    0.48
    Activations Density 0.038%

    No Known Activations