© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7628
    Prev
    Next
    INDEX
    Explanations

    comparative terms and phrases that highlight differences and advantages over competitors

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

    comparison or differentiation

    np_acts-logits-general · gemini-2.0-flash

    rivals, competitors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.64
    AndEndTag
    -0.62
    enderror
    -0.61
    NameInMap
    -0.59
    setVerticalGroup
    -0.58
    yntaxException
    -0.56
    ſelben
    -0.55
    bolista
    -0.54
     للاسماء
    -0.54
    存于互联网档案馆
    -0.53
    POSITIVE LOGITS
     competitors
    2.14
     competitor
    1.95
     rivals
    1.88
     rival
    1.88
     competing
    1.80
     Competitors
    1.68
     rivales
    1.46
     Konkurrenz
    1.44
    competi
    1.44
     конкурен
    1.43
    Activations Density 0.499%

    No Known Activations