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. 23-GEMMASCOPE-RES-16K
    6. 12324
    Prev
    Next
    INDEX
    Explanations

    instances and details about endangered species, particularly rhinos

    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
     Pyrene
    -0.67
    TestingModule
    -0.54
     ewes
    -0.52
    NamedQueries
    -0.51
     Loch
    -0.51
     Tsar
    -0.51
    detectChanges
    -0.51
     joaat
    -0.50
     olympiques
    -0.49
    ူ
    -0.48
    POSITIVE LOGITS
     Indonesia
    1.73
     Indonesian
    1.71
    Indonesia
    1.47
     Indones
    1.44
     Jakarta
    1.34
     Malaysia
    1.32
     Malaysian
    1.30
     Singapore
    1.28
     INDONESIA
    1.25
     Indon
    1.24
    Activations Density 0.274%

    No Known Activations