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. 9-GEMMASCOPE-RES-16K
    6. 1634
    Prev
    Next
    INDEX
    Explanations

    mentions of significant historical events and their impacts

    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
     <<<<<<<<<<<<<<
    -0.62
     bParam
    -0.56
     Exacts
    -0.54
    nEnter
    -0.53
    Datuak
    -0.53
    presso
    -0.53
     تضيفلها
    -0.52
    Бележки
    -0.52
    bekistan
    -0.51
     ويكيميديا
    -0.50
    POSITIVE LOGITS
     accidente
    0.70
     injuries
    0.68
     casualties
    0.68
     casualty
    0.66
     accident
    0.63
    WriteTagHelper
    0.62
     injury
    0.62
     traumat
    0.61
     trauma
    0.60
     traumatic
    0.59
    Activations Density 0.579%

    No Known Activations