© 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. 9-GEMMASCOPE-RES-16K
    11. 1630
    Prev
    Next
    INDEX
    Explanations

    phrases that include definite articles or demonstrative pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.89
     '\\;'
    -0.80
    __":
    -0.77
    }`}>
    -0.71
    脚注の使い方
    -0.69
    __*/
    -0.68
    __':
    -0.68
    }`).
    -0.64
    __":
    -0.64
    addGap
    -0.64
    POSITIVE LOGITS
     Iconic
    0.64
     crappy
    0.60
     pesky
    0.60
    ন্দ
    0.57
     اون
    0.56
     prettiest
    0.55
     annoying
    0.54
     виправивши
    0.54
     darn
    0.53
     little
    0.52
    Activations Density 0.353%

    No Known Activations