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. 25-GEMMASCOPE-RES-16K
    6. 7950
    Prev
    Next
    INDEX
    Explanations

    programming terms related to data handling and request/response operations

    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
     Covington
    -0.60
     Auburn
    -0.60
    iLocal
    -0.58
     Federated
    -0.57
     feather
    -0.54
     Scu
    -0.53
     chord
    -0.52
     Heim
    -0.52
     Korn
    -0.51
     Melan
    -0.51
    POSITIVE LOGITS
     req
    2.55
    req
    2.54
    Req
    1.97
     Req
    1.89
    REQ
    1.76
     REQ
    1.67
    reqs
    1.59
     Requ
    1.34
     requ
    1.34
    Requ
    1.29
    Activations Density 0.191%

    No Known Activations