© 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. 14-GEMMASCOPE-RES-16K
    11. 10318
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to large datasets or statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.91
    دانشنامهٔ
    -0.91
     ThemeData
    -0.88
     greateſt
    -0.81
    RectangleBorder
    -0.77
     Anſ
    -0.76
    Fordítás
    -0.73
    kháu
    -0.72
     houſe
    -0.72
     ſmall
    -0.72
    POSITIVE LOGITS
    endpush
    0.55
    <bos>
    0.53
    Vidite
    0.51
    はじめに
    0.49
     analysed
    0.46
    ),
    0.44
    出版年
    0.43
     
    0.43
    fiés
    0.43
    Anal
    0.43
    Activations Density 0.172%

    No Known Activations