© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1903
    Prev
    Next
    INDEX
    Explanations

    instances of the word "being" and its variations

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

    the passive voice construction "being" followed by past participles.

    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
     Offisielt
    -0.51
     ſeveral
    -0.48
     volando
    -0.46
     parlant
    -0.45
     Cæsar
    -0.45
     ſon
    -0.45
     houſe
    -0.44
     sanitarios
    -0.43
     becauſe
    -0.43
     themſelves
    -0.43
    POSITIVE LOGITS
    ness
    0.64
     touted
    0.47
    jsdelivr
    0.44
    ציה
    0.43
     كورة
    0.42
     lenker
    0.41
    ful
    0.40
    NESS
    0.40
    gien
    0.40
    usion
    0.40
    Activations Density 0.123%

    No Known Activations