© 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. 35-GEMMASCOPE-RES-16K
    11. 14415
    Prev
    Next
    INDEX
    Explanations

    references to political factions and their dynamics

    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
     pleaſure
    -0.52
     purpoſe
    -0.44
     Democratic
    -0.43
     left
    -0.42
     fatis
    -0.37
    民主党
    -0.37
     diffraction
    -0.37
     Left
    -0.37
     democratic
    -0.37
    twimg
    -0.37
    POSITIVE LOGITS
     conservative
    1.48
     conservatives
    1.36
     conservatism
    1.34
    conservative
    1.32
     konserv
    1.30
    Conservative
    1.28
    Conserv
    1.27
     Conservative
    1.27
    conserv
    1.23
    保守
    1.20
    Activations Density 0.622%

    No Known Activations