© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1775
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals and political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    )))));
    -0.56
    RTSN
    -0.54
    æa
    -0.53
    ceaux
    -0.52
    ̃
    -0.51
    tula
    -0.51
    kindle
    -0.50
    alised
    -0.50
    tés
    -0.49
    stir
    -0.49
    POSITIVE LOGITS
    PreferredItem
    1.07
    principalTable
    0.99
     Italijani
    0.92
    ArrowToggle
    0.85
    AndEndTag
    0.85
     المعيارى
    0.85
     Normdatei
    0.84
     nahilalakip
    0.80
    ItemBackground
    0.79
    URLException
    0.76
    Activations Density 0.284%

    No Known Activations