© 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. 8587
    Prev
    Next
    INDEX
    Explanations

    instructions and procedural language related to claims and benefits

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

    Follows common function words

    np_acts-logits-general · gemini-2.0-flash

    advice and claims

    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
    已然
    -1.00
    に於
    -0.98
     resourceCulture
    -0.95
     annum
    -0.94
    bkz
    -0.94
     således
    -0.91
     requisite
    -0.90
     gänzlich
    -0.89
     iż
    -0.89
     replete
    -0.86
    POSITIVE LOGITS
     lots
    0.97
     people
    0.83
    Lots
    0.82
    いろいろな
    0.80
     kinds
    0.78
     really
    0.77
     things
    0.76
     jeito
    0.76
     usato
    0.74
     colère
    0.74
    Activations Density 1.391%

    No Known Activations