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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 13459
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "about" or topics being introduced

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.84
    BeginInit
    -0.82
     neceff
    -0.79
     ſtate
    -0.75
    QMetaType
    -0.74
    rachtet
    -0.73
     fevere
    -0.72
     Majefty
    -0.71
     Houſe
    -0.71
     Reſ
    -0.70
    POSITIVE LOGITS
     about
    3.81
    about
    3.17
     ABOUT
    2.90
     About
    2.87
    About
    2.83
    ABOUT
    2.46
     tentang
    2.36
    bout
    2.10
     abt
    2.01
     apie
    2.01
    Activations Density 0.134%

    No Known Activations