© 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. 24-GEMMASCOPE-RES-16K
    11. 11153
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or variables in a technical context

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

    Expressions with exponents (**) and numbers

    np_acts-logits-general · gemini-2.0-flash

    2 followed by 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twice
    -1.17
     twice
    -1.16
     Twice
    -1.13
    Twice
    -1.09
     double
    -1.05
     doble
    -1.05
     Third
    -0.96
    Third
    -0.94
     Double
    -0.92
     doubled
    -0.89
    POSITIVE LOGITS
    deviantart
    0.51
    ieteur
    0.48
     springfox
    0.47
     ljud
    0.43
    yoti
    0.43
    őz
    0.43
     Schenk
    0.42
    FRP
    0.42
    ósito
    0.42
     Monsanto
    0.42
    Activations Density 0.264%

    No Known Activations