© 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. 9-GEMMASCOPE-RES-16K
    11. 7859
    Prev
    Next
    INDEX
    Explanations

    content related to ratings and classifications of media, particularly focusing on explicit or graphic themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    rungsseite
    -0.43
     négociations
    -0.40
     fashion
    -0.37
    Predecesor
    -0.37
    DockStyle
    -0.37
     Così
    -0.36
    gameserver
    -0.35
     negotiating
    -0.35
    IsPostBack
    -0.35
     kym
    -0.34
    POSITIVE LOGITS
     censored
    0.60
     censor
    0.59
    gory
    0.50
     Cens
    0.50
    censored
    0.49
     gory
    0.49
     explicit
    0.48
    adult
    0.47
     PG
    0.47
     IBOutlet
    0.47
    Activations Density 0.240%

    No Known Activations