© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8741
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to observational data analysis and astrophysics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Capacity
    -0.30
     sorti
    -0.30
     capacity
    -0.29
     والأ
    -0.27
     shoes
    -0.27
    ↵↵
    -0.27
     Capacity
    -0.26
     sucedido
    -0.26
    btnSave
    -0.25
    capacity
    -0.25
    POSITIVE LOGITS
    SharedDtor
    0.99
    PhysRevD
    0.99
     neutrino
    0.88
     neutrinos
    0.87
     galaxies
    0.82
    trino
    0.82
    يكب
    0.82
     CERN
    0.80
    PhysRev
    0.79
    ativistic
    0.79
    Activations Density 2.884%

    No Known Activations