© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15020
    Prev
    Next
    INDEX
    Explanations

    references to various types of films, particularly American films, and the structure of programming code

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

    Code or identifiers followed by specific terms

    np_acts-logits-general · gemini-2.0-flash

    punctuation and identifiers

    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
     but
    -0.56
    別
    -0.55
     de
    -0.53
     But
    -0.53
    But
    -0.49
     De
    -0.49
     Be
    -0.48
     Don
    -0.48
     Brand
    -0.47
     David
    -0.47
    POSITIVE LOGITS
     jScrollPane
    0.98
    脚注の使い方
    0.95
     Theſe
    0.93
     Савезне
    0.91
     Roskov
    0.90
     myſelf
    0.87
    出版年
    0.86
     pleaſure
    0.86
    ंदीखरीदारी
    0.85
    protoimpl
    0.84
    Activations Density 0.188%

    No Known Activations