© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11107
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and sharing ideas or experiences

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

    Sharing of knowledge or experiences

    np_acts-logits-general · gemini-2.0-flash

    sharing ideas and knowledge

    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
    olden
    -0.48
    chowa
    -0.47
    parentElement
    -0.45
     يتيمه
    -0.45
    urlopen
    -0.45
     برخورد
    -0.43
    XMLHttpRequest
    -0.42
    kelen
    -0.42
    riever
    -0.42
    epik
    -0.42
    POSITIVE LOGITS
     ideas
    1.39
     learnings
    1.22
     concepts
    1.21
     knowledge
    1.15
    ագրություններ
    1.15
     findings
    1.09
    ideas
    1.08
     expertise
    1.03
     Ideas
    0.97
    concepts
    0.97
    Activations Density 0.401%

    No Known Activations