© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7638
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating the extent or degree of something

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

    the phrase "as much as possible" (or similar comparative constructions expressing maximum extent or degree).

    oai_token-act-pair · claude-4-5-haikuTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    quiagem
    -0.50
    îtres
    -0.37
     Souhaitez
    -0.37
     hochzeit
    -0.36
    Rüyada
    -0.36
    NamedQueries
    -0.36
    并未
    -0.35
    紆
    -0.35
    disfraz
    -0.35
    postsleuth
    -0.35
    POSITIVE LOGITS
     possible
    2.73
    possible
    2.27
     Possible
    2.16
    Possible
    2.11
     possível
    2.03
     posible
    2.00
     POSSIBLE
    1.95
     possibile
    1.92
     poffible
    1.87
     posibles
    1.75
    Activations Density 0.199%

    No Known Activations