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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12975
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to programming and technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arXiv
    -0.66
     consulter
    -0.54
    </thead>
    -0.51
    uga
    -0.50
     Castro
    -0.49
     moment
    -0.48
     Ge
    -0.47
     Dorado
    -0.47
    lı
    -0.46
     merk
    -0.46
    POSITIVE LOGITS
    Fax
    1.48
     Fax
    1.45
     fax
    1.31
     FAX
    1.30
    fax
    1.27
    FAX
    1.27
    enumi
    1.10
    AddTagHelper
    1.02
     '\\;'
    1.02
    berdayakan
    1.00
    Activations Density 0.026%

    No Known Activations