© 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. 3-GEMMASCOPE-RES-16K
    11. 1294
    Prev
    Next
    INDEX
    Explanations

    the word "almost" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     culoare
    -0.73
     yoksa
    -0.68
     numele
    -0.66
     viață
    -0.66
     lugs
    -0.66
     urma
    -0.66
     domicilio
    -0.65
     Murdock
    -0.64
     cirrhosis
    -0.63
     mayores
    -0.63
    POSITIVE LOGITS
     almost
    2.89
    Almost
    2.65
     Almost
    2.64
    almost
    2.63
     nearly
    2.44
    nearly
    2.15
     Nearly
    2.06
     presque
    2.04
     hampir
    2.03
    Nearly
    1.98
    Activations Density 0.042%

    No Known Activations