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. 23-GEMMASCOPE-RES-16K
    6. 8944
    Prev
    Next
    INDEX
    Explanations

    phrases associated with collaborations or partnerships in business contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mifflin
    -0.54
    новниш
    -0.53
    Tikang
    -0.53
     Meksiku
    -0.49
    Vidite
    -0.49
     OFDb
    -0.48
     Paglinawan
    -0.48
    Билгалдахарш
    -0.47
    Jeografia
    -0.47
    فحه
    -0.47
    POSITIVE LOGITS
     Ar
    3.07
     ar
    2.97
    Ar
    2.85
     AR
    2.71
    AR
    2.12
     Ар
    2.08
    ar
    2.03
    Ар
    2.00
     ар
    1.98
     arc
    1.78
    Activations Density 0.340%

    No Known Activations