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. 4-GEMMASCOPE-RES-16K
    6. 810
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a conclusion or decision-making process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yonder
    -0.75
     Siberian
    -0.70
     Ural
    -0.68
     Hodgkin
    -0.68
     houſe
    -0.67
     galore
    -0.65
     Houſe
    -0.65
     Shetland
    -0.63
     mignon
    -0.63
     Byzantine
    -0.63
    POSITIVE LOGITS
    Rohy
    0.74
     reach
    0.66
     kasarigan
    0.63
    Personensuche
    0.61
     estimés
    0.60
     désolés
    0.59
    iecie
    0.58
     samlet
    0.55
     néglig
    0.54
    بوابة
    0.54
    Activations Density 0.153%

    No Known Activations