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. 25-GEMMASCOPE-RES-16K
    6. 12467
    Prev
    Next
    INDEX
    Explanations

    references to rare or endangered species

    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
     Georgia
    -0.57
     Pyrene
    -0.53
    Georgia
    -0.52
     Fulton
    -0.51
    Quebec
    -0.50
     Dá
    -0.50
     Protobuf
    -0.50
     Tees
    -0.48
     Quebec
    -0.47
    WillAppear
    -0.47
    POSITIVE LOGITS
     Indonesian
    1.31
     Indonesia
    1.29
     Jakarta
    1.22
    Indonesia
    1.13
     Indones
    1.11
    Jakarta
    1.07
     Bali
    0.96
    indonesia
    0.95
     INDONESIA
    0.95
     indonesia
    0.94
    Activations Density 0.081%

    No Known Activations