© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 12086
    Prev
    Next
    INDEX
    Explanations

    terms related to professional writing and expertise in essay composition

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

    tokens that refer to people — names, usernames, or person/titles (proper names and role labels).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.70
     فريبيس
    -0.68
    aarrggbb
    -0.63
     MainAxisSize
    -0.60
    Hentet
    -0.60
    RegressionTest
    -0.59
     disambiguazione
    -0.58
    IntoConstraints
    -0.57
    
    -0.56
    蚪
    -0.56
    POSITIVE LOGITS
    ConstraintMaker
    0.38
     Rogan
    0.34
     móvel
    0.33
    statt
    0.33
     Robson
    0.32
    <eos>
    0.32
    ↵
    0.31
     
    0.31
    term
    0.31
     Ross
    0.31
    Activations Density 0.000%

    No Known Activations