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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 15386
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new section or topic in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵↵↵↵
    -0.49
    ):
    -0.48
    ík
    -0.48
    によっては
    -0.45
     gr
    -0.44
     (?)
    -0.42
     «
    -0.42
     he
    -0.42
    まあ
    -0.42
     "/",
    -0.42
    POSITIVE LOGITS
    出版年
    0.98
    XmlAccessType
    0.86
    脚注の使い方
    0.86
    providedIn
    0.80
    #
    0.80
     فريبيس
    0.78
     للمعارف
    0.74
    DockStyle
    0.73
     nahilalakip
    0.71
    ."</
    0.70
    Activations Density 0.218%

    No Known Activations