© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 61
    Prev
    Next
    INDEX
    Explanations

    numerical representations of data or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical values and their associated data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    0.0f, 0, 0 coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imageshack
    -0.86
    Datuak
    -0.81
    Autoritní
    -0.79
    ]$}
    -0.78
    --)
    -0.76
    AndroidJUnit
    -0.75
    ...");
    -0.68
    …]
    -0.67
    queryInterface
    -0.67
    Bibliograf
    -0.66
    POSITIVE LOGITS
    UnusedPrivate
    0.61
    (!__
    0.46
     déchir
    0.45
     prière
    0.44
     coloridas
    0.41
     vermelhas
    0.41
     volonté
    0.39
     brancas
    0.39
     calme
    0.38
     calm
    0.38
    Activations Density 0.229%

    No Known Activations