© 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. 3268
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential benefits and outcomes for individuals or groups

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

    phrases expressing potential advantages or positive outcomes using "would/could/might" combined with "benefit."

    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
    ագրություններ
    -0.40
     Autorisations
    -0.37
    belea
    -0.35
    癖
    -0.34
    ंदीखरीदारी
    -0.34
    AndEndTag
    -0.34
    Обе
    -0.33
    "}")
    -0.32
    eh
    -0.32
     puk
    -0.32
    POSITIVE LOGITS
     benefit
    2.45
     benefited
    2.42
     benefitted
    2.30
    benefit
    2.22
    Benefit
    2.13
     benefiting
    2.11
     Benefit
    2.05
     benefits
    1.95
    benef
    1.79
    benefits
    1.73
    Activations Density 0.412%

    No Known Activations