© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2918
    Prev
    Next
    INDEX
    Explanations

    sections of an email or document that indicate recipients and subjects

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

    title:

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    чан
    -0.42
    больше
    -0.41
     mũi
    -0.41
    ura
    -0.41
     هو
    -0.41
    umi
    -0.40
    ズム
    -0.40
     avuto
    -0.40
    ceed
    -0.40
     cuchillo
    -0.40
    POSITIVE LOGITS
    BeginContext
    0.91
    Билгалдахарш
    0.90
     мәкал
    0.88
    躇
    0.85
     disambiguazione
    0.84
    UnusedPrivate
    0.81
    ]")]
    0.80
     Pingback
    0.79
     surla
    0.79
     ujednoznacz
    0.77
    Activations Density 0.004%

    No Known Activations