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. 19-GEMMASCOPE-RES-16K
    6. 600
    Prev
    Next
    INDEX
    Explanations

    phrases related to local surroundings and community-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Auditorium
    -0.52
    Staff
    -0.51
    offices
    -0.51
     Offices
    -0.50
     prisons
    -0.48
     holo
    -0.48
     Aluno
    -0.48
     offices
    -0.47
    Referee
    -0.47
    ieuses
    -0.47
    POSITIVE LOGITS
     backyard
    1.56
     driveway
    1.43
     yard
    1.38
     Backyard
    1.16
     garden
    1.15
     neighbors
    1.08
     lawn
    1.04
     garage
    1.03
    yard
    1.03
     neighborhood
    1.00
    Activations Density 0.140%

    No Known Activations