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. 3-GEMMASCOPE-RES-16K
    6. 16156
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating quantity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -1.01
     raiſ
    -0.85
     fevere
    -0.84
     purpoſe
    -0.82
    ſelves
    -0.81
     myſelf
    -0.81
     occaf
    -0.80
     themſelves
    -0.80
     fubject
    -0.79
     ſtate
    -0.78
    POSITIVE LOGITS
     più
    1.40
     más
    1.39
     máis
    1.18
     mais
    1.15
     més
    1.10
     piu
    1.07
    más
    1.02
    più
    0.99
     MÁS
    0.93
     Mais
    0.90
    Activations Density 0.055%

    No Known Activations