© 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. 2987
    Prev
    Next
    INDEX
    Explanations

    information related to biotechnology and scientific advancements

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

    Preceding tokens before a period or company name

    np_acts-logits-general · gemini-2.0-flash

    various languages, proper nouns

    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
    Apparently
    -0.55
     Apparently
    -0.52
     due
    -0.49
    ↵↵
    -0.48
     apparently
    -0.48
     Zwar
    -0.47
      
    -0.46
     &
    -0.46
     ca
    -0.45
     just
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.92
    رشف
    0.90
     дописавши
    0.83
     hâte
    0.81
     Shakspeare
    0.80
     missione
    0.80
     صوتيه
    0.79
     Efq
    0.79
     verdens
    0.78
     pleaſure
    0.76
    Activations Density 0.159%

    No Known Activations