© 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. 20-GEMMASCOPE-RES-16K
    11. 838
    Prev
    Next
    INDEX
    Explanations

    specific entities and locations related to places and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    relative pronouns and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Odkazy
    -0.73
     numberOfRows
    -0.64
    addPreferredGap
    -0.63
    ItemBackground
    -0.62
    /}.
    -0.61
    VIAF
    -0.60
    ########.
    -0.60
    addContainerGap
    -0.59
     ISNI
    -0.58
    erschiedene
    -0.58
    POSITIVE LOGITS
     who
    2.03
    who
    1.50
     whom
    1.38
     whose
    1.13
    whom
    1.07
    Who
    1.05
     quien
    0.98
     Who
    0.96
    whose
    0.95
     którzy
    0.91
    Activations Density 0.418%

    No Known Activations