© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38-GEMMASCOPE-RES-16K
    11. 11558
    Prev
    Next
    INDEX
    Explanations

    mentions of digital advertising and its characteristics compared to traditional advertising

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.55
    MessageState
    -0.49
     ExecuteAsync
    -0.48
    adaptiveStyles
    -0.45
    hubanes
    -0.40
    providedIn
    -0.39
    ="@+
    -0.39
     autorytatywna
    -0.38
    +#+#
    -0.37
    ErrUnexpectedEOF
    -0.35
    POSITIVE LOGITS
     traditional
    2.16
    traditional
    1.94
    Traditional
    1.90
     Traditional
    1.84
    传统
    1.75
     tradicional
    1.70
     trady
    1.70
     tradicionales
    1.63
    傳統
    1.63
     tradizionale
    1.63
    Activations Density 1.160%

    No Known Activations