Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8430
    Prev
    Next
    INDEX
    Explanations

    terms related to atomic structures and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    таратура
    -0.70
     تضيفلها
    -0.70
    mender
    -0.67
    EndProject
    -0.65
     credentials
    -0.62
     Kolo
    -0.61
     schme
    -0.61
    Calla
    -0.60
    orthodox
    -0.60
     Nolan
    -0.57
    POSITIVE LOGITS
     atomic
    1.17
     ATOM
    1.13
     atom
    1.12
    Atomic
    1.07
    atom
    1.07
     Atom
    1.04
     atoms
    1.01
     Atomic
    1.00
     ato
    1.00
     Atoms
    0.99
    Activations Density 0.099%

    No Known Activations