© 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. 3-GEMMASCOPE-RES-16K
    11. 5818
    Prev
    Next
    INDEX
    Explanations

    references to different republics or political entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.64
     Scher
    -0.53
     anglès
    -0.53
     CreateTagHelper
    -0.51
    AnchorStyles
    -0.51
    djangoproject
    -0.49
    сшта
    -0.47
     Kem
    -0.47
    IntoConstraints
    -0.47
    ริง
    -0.46
    POSITIVE LOGITS
    ong
    0.86
    CrossRef
    0.85
    TagMode
    0.84
     Republic
    0.84
     lazy
    0.76
    Republic
    0.76
     republic
    0.75
    ONG
    0.74
     المعيارى
    0.74
     Lazy
    0.73
    Activations Density 0.757%

    No Known Activations