© 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. 20-GEMMASCOPE-RES-16K
    11. 8612
    Prev
    Next
    INDEX
    Explanations

    parameters and their values in code documentation

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

    Prepositions and determiners

    np_acts-logits-general · gemini-2.0-flash

    state space types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -1.03
    enumi
    -0.79
    __*/
    -0.67
    StoryboardSegue
    -0.64
    ✨:
    -0.62
     Autorizaciones
    -0.61
     betweenstory
    -0.60
    ftagPool
    -0.59
    aarrggbb
    -0.59
     renewals
    -0.57
    POSITIVE LOGITS
     to
    0.78
     used
    0.75
    ที่จะ
    0.74
     who
    0.66
     whose
    0.65
     must
    0.65
    addContainerGap
    0.63
     بيها
    0.63
     cui
    0.63
     which
    0.62
    Activations Density 0.308%

    No Known Activations