© 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. 16-GEMMASCOPE-RES-16K
    11. 3993
    Prev
    Next
    INDEX
    Explanations

    structural elements and punctuation in complex expressions

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

    Tokens after bracketed expressions

    np_acts-logits-general · gemini-2.0-flash

    hosting options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avyzd
    -0.55
     BitmapFactory
    -0.54
    بوابة
    -0.52
    eddable
    -0.50
     bootstra
    -0.50
    ="#"><
    -0.50
    tanleria
    -0.49
    localVar
    -0.48
    toggler
    -0.48
    Enciclopedia
    -0.48
    POSITIVE LOGITS
     propOrder
    0.68
     setCode
    0.61
     reference
    0.61
     REFERENCE
    0.59
    reference
    0.59
     références
    0.59
     onOptions
    0.58
    Tikang
    0.56
    Sucesor
    0.56
    age
    0.56
    Activations Density 0.787%

    No Known Activations