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. 25-GEMMASCOPE-RES-16K
    6. 5810
    Prev
    Next
    INDEX
    Explanations

    references to technical setup and configuration instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌آمباردا
    -0.55
     which
    -0.52
     melainkan
    -0.44
     ويكيميديا
    -0.43
    ┛
    -0.42
    Carriera
    -0.42
     förm
    -0.42
    uxxxx
    -0.41
    Viitteet
    -0.41
     Alternatively
    -0.41
    POSITIVE LOGITS
    和
    1.91
     и
    1.88
     và
    1.83
     and
    1.76
    และ
    1.62
     και
    1.62
     AND
    1.61
     和
    1.58
     și
    1.54
     और
    1.50
    Activations Density 0.033%

    No Known Activations