© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3082
    Prev
    Next
    INDEX
    Explanations

    varied expressions of degree, particularly those indicating extent or comparison

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    the word "way" used as an intensifier or adverb meaning "excessively" or "very much."

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     فريبيس
    -0.65
    __":
    -0.62
     queſta
    -0.56
    PhysRevD
    -0.55
    Rptr
    -0.54
    Становништво
    -0.53
    CompleteListener
    -0.51
    tinyos
    -0.50
    /**
    -0.49
    +:+
    -0.49
    POSITIVE LOGITS
     too
    0.62
     WAY
    0.44
     more
    0.42
     TOO
    0.42
     quá
    0.42
     way
    0.41
    troppo
    0.41
     beyond
    0.40
     excessive
    0.40
    too
    0.39
    Activations Density 0.169%

    No Known Activations