© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10651
    Prev
    Next
    INDEX
    Explanations

    directional phrases and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noqa
    -0.52
     strconv
    -0.50
    CTL
    -0.49
    ungkinan
    -0.48
    parameter
    -0.48
     parameter
    -0.48
    +#+#
    -0.47
    interopRequire
    -0.46
    峻
    -0.45
    гле
    -0.44
    POSITIVE LOGITS
     itſelf
    0.88
    contentLoaded
    0.85
    ̍t
    0.83
    تقاوى
    0.81
    ]")]
    0.80
     myſelf
    0.79
     AssemblyVersion
    0.74
    ftagPool
    0.73
    !")
    0.72
    ſelf
    0.72
    Activations Density 0.240%

    No Known Activations