© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 14388
    Prev
    Next
    INDEX
    Explanations

    references to peer involvement and hierarchical structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getItemCount
    -0.75
     Greenberg
    -0.67
     Krueger
    -0.66
    rice
    -0.66
     maraming
    -0.66
    awtextra
    -0.65
    konomi
    -0.65
     tri
    -0.65
     Calhoun
    -0.65
     Theron
    -0.64
    POSITIVE LOGITS
     Wim
    0.84
    +#+
    0.83
    wim
    0.82
    Wim
    0.78
     bifur
    0.78
    unhofer
    0.77
     Aha
    0.76
     winked
    0.76
    Alder
    0.76
     Tacitus
    0.76
    Activations Density 0.562%

    No Known Activations