© 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 EvalsExportsAPI 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. 10269
    Prev
    Next
    INDEX
    Explanations

    functional programming constructs and testing patterns in code

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

    Begins with a parenthesis or quotation mark

    np_acts-logits-general · gemini-2.0-flash

    testing expectations and correctness

    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
    SupportActionBar
    -0.54
    UrlResolution
    -0.50
    Reprints
    -0.47
    enumi
    -0.46
    [*
    -0.46
     ((*
    -0.45
    OpenHelper
    -0.45
     [*
    -0.45
     (*
    -0.43
     […]
    -0.43
    POSITIVE LOGITS
     correctly
    1.00
    correctly
    0.94
     doesnt
    0.85
     Should
    0.84
    Should
    0.83
     shouldnt
    0.83
     correct
    0.82
    Correct
    0.81
     wrong
    0.81
    RegressionTest
    0.81
    Activations Density 0.182%

    No Known Activations