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. 5-GEMMASCOPE-RES-16K
    6. 2052
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réguli
    -0.47
     tanpa
    -0.46
    Lähteet
    -0.44
     output
    -0.44
    divarius
    -0.44
     powerful
    -0.44
     vær
    -0.44
     most
    -0.43
     without
    -0.43
    kå
    -0.43
    POSITIVE LOGITS
     متعلقه
    1.26
     relating
    1.24
     pertain
    1.22
     pertaining
    1.20
     pertains
    1.18
     '\\;'
    1.11
     concerning
    1.07
    Concerning
    1.03
     regarding
    1.02
     Concerning
    1.02
    Activations Density 0.351%

    No Known Activations