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. 16-GEMMASCOPE-RES-16K
    6. 8904
    Prev
    Next
    INDEX
    Explanations

    verbs related to learning and the act of acquiring knowledge or skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the concept of "learning"

    np_acts-logits-general · gemini-2.0-flash

    learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coff
    -0.51
     mis
    -0.51
    timus
    -0.49
     nhàng
    -0.48
    我没
    -0.48
    fullWidth
    -0.48
     satel
    -0.47
     canlynol
    -0.47
    ilius
    -0.47
    мирование
    -0.47
    POSITIVE LOGITS
    LEARN
    1.13
     learns
    1.09
     LEARN
    1.06
    Lear
    0.98
    Learn
    0.97
     learn
    0.96
     learnt
    0.95
    learn
    0.94
     Learn
    0.91
     learner
    0.91
    Activations Density 0.083%

    No Known Activations