© 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. 4672
    Prev
    Next
    INDEX
    Explanations

    SQL-related keywords and operations, particularly those concerned with sorting and filtering data

    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
    enumii
    -0.86
     Réponses
    -0.72
     تضيفلها
    -0.71
     autorytatywna
    -0.67
    RenderAtEndOf
    -0.66
     estimés
    -0.63
    JMenuBar
    -0.63
    })));
    -0.62
    Autoritní
    -0.61
    styleable
    -0.61
    POSITIVE LOGITS
    OwnProperty
    0.48
     inequality
    0.47
    toBeTruthy
    0.47
    ostat
    0.46
     lexic
    0.46
    mazoo
    0.45
    над
    0.45
     Delgado
    0.45
    ξης
    0.45
    down
    0.44
    Activations Density 0.993%

    No Known Activations