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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5050
    Prev
    Next
    INDEX
    Explanations

    JSON formatted data structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tearDown
    -0.78
    ImageContext
    -0.77
    AsUp
    -0.76
    المناصب
    -0.73
    igslist
    -0.70
    NameInMap
    -0.69
     }}"></
    -0.67
    AnchorStyles
    -0.64
     Him
    -0.63
     ruine
    -0.63
    POSITIVE LOGITS
    +"
    1.31
    +"'
    1.31
    ":"
    1.13
    ()+"
    1.13
    +'
    0.95
    ]+"
    0.95
    +"\
    0.92
    +":
    0.91
    )+"
    0.89
     +"
    0.85
    Activations Density 0.150%

    No Known Activations