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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 923
    Prev
    Next
    INDEX
    Explanations

    references to audience engagement and representation in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.48
     utafitiHapana
    -0.48
     resourceCulture
    -0.48
    NewUrlParser
    -0.47
     мәкал
    -0.45
     كومونز
    -0.44
     &___
    -0.43
     незавершена
    -0.43
     autorytatywna
    -0.41
     ModelExpression
    -0.41
    POSITIVE LOGITS
     audience
    3.05
     audiences
    2.80
     viewers
    2.78
    audience
    2.39
     viewer
    2.39
     readers
    2.36
     Audience
    2.30
     listeners
    2.23
    Audience
    2.23
    观众
    2.13
    Activations Density 0.574%

    No Known Activations