© 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. 7025
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to the construction and operation of scientific apparatus or devices

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

    "ex" prefixes or "exon"

    np_acts-logits-general · gemini-2.0-flash

    ex, Ex, exon

    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
    SizeF
    -0.53
    Hochspringen
    -0.51
    μει
    -0.50
     aidant
    -0.49
    modelBuilder
    -0.49
    principalTable
    -0.49
    MLLoader
    -0.48
    AVEL
    -0.48
    SOUNDBITE
    -0.47
     altrett
    -0.47
    POSITIVE LOGITS
     ex
    4.55
     Ex
    4.30
    Ex
    4.13
    ex
    4.05
     EX
    3.38
    EX
    3.20
     eks
    2.29
     exh
    2.13
     exc
    2.12
     exon
    1.98
    Activations Density 0.533%

    No Known Activations