Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 13800
    Prev
    Next
    INDEX
    Explanations

    references to medical research, particularly around genetics and treatments

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

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    technical terms and specific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.86
     purpoſe
    -0.82
     leaſt
    -0.81
     pleaſure
    -0.79
     themſelves
    -0.78
     ſeveral
    -0.77
     reaſon
    -0.75
     houſe
    -0.71
     ſtate
    -0.71
     Efq
    -0.71
    POSITIVE LOGITS
     is
    1.93
     has
    1.77
     was
    1.45
     can
    1.44
     will
    1.41
     isn
    1.29
     doesn
    1.29
     hasn
    1.24
     may
    1.21
     goes
    1.21
    Activations Density 1.457%

    No Known Activations