© 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. 41-GEMMASCOPE-RES-16K
    11. 7345
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss the consequences of actions or events in various contexts, particularly focusing on issues of division, law, and social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.50
    tvguidetime
    -0.43
    RefNanny
    -0.43
    webElementXpaths
    -0.43
    ViewImports
    -0.36
    endmodule
    -0.36
    aktery
    -0.34
    strix
    -0.34
    jé
    -0.33
    ніципа
    -0.33
    POSITIVE LOGITS
     exacerbate
    1.52
     exacerb
    1.44
     exacerbated
    1.40
     exacer
    1.34
     compounding
    1.34
     worsen
    1.32
     worsened
    1.30
     amplify
    1.27
     intensify
    1.27
     amplified
    1.23
    Activations Density 0.771%

    No Known Activations