© 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. 18-GEMMASCOPE-RES-16K
    11. 2882
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement and critique

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

    preceding "improvement" or "improve"

    np_acts-logits-general · gemini-2.0-flash

    room for improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    しまう
    -0.42
    fortawesome
    -0.41
     lệ
    -0.40
     
    -0.40
    しまいます
    -0.37
    OSE
    -0.36
    liert
    -0.36
    ю
    -0.36
    祟
    -0.35
     setuptools
    -0.35
    POSITIVE LOGITS
     improvement
    2.80
     improvements
    2.63
     Improvement
    2.51
    improvement
    2.50
    improve
    2.41
    Improvement
    2.39
     Improvements
    2.38
     IMPROVEMENT
    2.33
     improve
    2.33
    Improvements
    2.32
    Activations Density 0.420%

    No Known Activations