© 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. 3-GEMMASCOPE-RES-16K
    6. 6662
    Prev
    Next
    INDEX
    Explanations

    references to intention and purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogaster
    -0.53
     hire
    -0.48
    modb
    -0.48
     vectorielle
    -0.47
     tarjo
    -0.46
    からず
    -0.45
    IM
    -0.45
    #+#
    -0.45
    irs
    -0.44
     amour
    -0.44
    POSITIVE LOGITS
     مرئيه
    0.92
    adaptiveStyles
    0.79
    UnitTesting
    0.76
    aarrggbb
    0.71
    "],
    
    0.70
    scriptId
    0.69
     Exacts
    0.68
    "])
    
    0.67
    createClass
    0.67
    setVerticalGroup
    0.65
    Activations Density 0.324%

    No Known Activations