© 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. 8075
    Prev
    Next
    INDEX
    Explanations

    entities and proper nouns related to companies and organizations

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

    company names and business entities.

    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
    Билгалдахарш
    -0.51
    хьтан
    -0.49
    harapkan
    -0.44
    TintMode
    -0.41
    oredCriteria
    -0.40
    SetBool
    -0.40
     estí
    -0.39
     kiệm
    -0.39
     Abends
    -0.39
    tangentMode
    -0.38
    POSITIVE LOGITS
     specializes
    1.09
     specialises
    1.05
     specialize
    1.02
     specialise
    1.02
     specializing
    0.98
     specialising
    0.95
     headquartered
    0.77
     занимается
    0.76
     specialized
    0.73
     specialised
    0.73
    Activations Density 0.391%

    No Known Activations