© 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. 35-GEMMASCOPE-RES-16K
    11. 14092
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to permission and authority in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.59
    ViewImports
    -0.55
     tartalomajánló
    -0.54
    endphp
    -0.51
    TagHelper
    -0.50
    :✨
    -0.49
    المناصب
    -0.47
    SourceChecksum
    -0.47
    Tikang
    -0.47
    
    -0.46
    POSITIVE LOGITS
     makes
    1.58
     helps
    1.47
     gives
    1.41
     brings
    1.30
     allows
    1.30
    makes
    1.28
     enables
    1.24
     ensures
    1.21
     means
    1.18
     implies
    1.16
    Activations Density 2.078%

    No Known Activations