© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2860
    Prev
    Next
    INDEX
    Explanations

    names of individuals and organizations involved in political or social 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
     CanadaChoose
    -0.84
    putable
    -0.57
     varandra
    -0.57
    ēju
    -0.57
     Haitian
    -0.56
    šanai
    -0.56
     iyon
    -0.54
     Afterward
    -0.52
    AVOR
    -0.52
    tahankan
    -0.51
    POSITIVE LOGITS
     India
    1.44
     Delhi
    1.39
     Mumbai
    1.36
    India
    1.32
     Indian
    1.30
    Delhi
    1.26
    Indian
    1.21
     INDIA
    1.20
    Mumbai
    1.19
     DELHI
    1.18
    Activations Density 1.462%

    No Known Activations