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. 25-GEMMASCOPE-RES-16K
    6. 12469
    Prev
    Next
    INDEX
    Explanations

    phrases related to funding and support for research initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Americans
    -0.76
     American
    -0.75
     AMERICAN
    -0.75
     Zacks
    -0.73
    American
    -0.71
     american
    -0.67
    Americans
    -0.67
    american
    -0.67
     Amerikan
    -0.66
    AMERICAN
    -0.66
    POSITIVE LOGITS
     Britain
    0.83
    Britain
    0.76
     UK
    0.75
    UK
    0.65
     BRITAIN
    0.65
     campaigning
    0.65
    Whilst
    0.64
     British
    0.63
     FTSE
    0.62
     behaviours
    0.60
    Activations Density 0.395%

    No Known Activations