© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 11500
    Prev
    Next
    INDEX
    Explanations

    specific references to individuals and their professional affiliations or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.53
    mittedly
    -0.47
    일에
    -0.45
    ultuous
    -0.45
     pro
    -0.44
     namelijk
    -0.43
    gá
    -0.42
    теры
    -0.42
     pé
    -0.41
    ë
    -0.41
    POSITIVE LOGITS
     Efq
    0.89
     myſelf
    0.76
     Jefus
    0.72
     againſt
    0.70
    தல்
    0.70
     Мексичка
    0.69
    ]--;
    0.69
    tvguidetime
    0.68
     becauſe
    0.65
     Chrift
    0.65
    Activations Density 0.353%

    No Known Activations