© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 14786
    Prev
    Next
    INDEX
    Explanations

    references to historical injustices and human rights violations

    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
    Tikang
    -0.54
     mysteriously
    -0.50
     Schwierigkeiten
    -0.50
     flattered
    -0.50
     curiosidad
    -0.49
    出版年
    -0.49
     anecd
    -0.49
    ernoo
    -0.48
    isamment
    -0.48
     modestly
    -0.47
    POSITIVE LOGITS
     disgusting
    1.38
     vile
    1.25
     horrible
    1.23
     despicable
    1.18
     cruel
    1.16
     horrific
    1.15
     horrifying
    1.13
     hideous
    1.06
     horrid
    1.05
     heinous
    1.05
    Activations Density 0.879%

    No Known Activations