© 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. 4604
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming syntax elements, particularly LaTeX-style math notation and code keywords.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @jbloomaus

    terms and variables related to computational structures and operations

    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
     برانيه
    -0.86
    Története
    -0.77
    ])):
    -0.70
     ModelExpression
    -0.70
     Mev
    -0.69
     LUMP
    -0.66
    )")
    -0.65
    ValueGeneration
    -0.65
    umenical
    -0.64
    läs
    -0.63
    POSITIVE LOGITS
     SN
    0.90
     SPS
    0.85
     SAC
    0.82
     SCS
    0.81
     Sarmiento
    0.79
    SAC
    0.78
     SBS
    0.78
     SRA
    0.78
     SMC
    0.77
    SB
    0.77
    Activations Density 7.123%

    No Known Activations