Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1834
    Prev
    Next
    INDEX
    Explanations

    references to academic journals and their articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.66
    SharedCtor
    -0.60
    RTLR
    -0.59
    hyrchwyd
    -0.58
    tagHelperRunner
    -0.56
    Referencies
    -0.56
    Diweddarwch
    -0.55
     betweenstory
    -0.55
    ########.
    -0.54
    PerformLayout
    -0.51
    POSITIVE LOGITS
    期刊论文
    0.54
     상세
    0.48
     journal
    0.44
     journals
    0.43
     publication
    0.42
    刊
    0.40
     Scopus
    0.40
     Journals
    0.40
     paper
    0.39
     出版
    0.38
    Activations Density 1.425%

    No Known Activations