© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3401
    Prev
    Next
    INDEX
    Explanations

    financial terms and classifications related to various sectors

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

    technical or professional service-related terms, such as SEO, data analysis, and academic/research terminology.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     виправивши
    -0.69
    principalTable
    -0.53
     mergeFrom
    -0.52
    Atsauces
    -0.51
     Monfieur
    -0.49
    MarshalTo
    -0.48
     bershka
    -0.48
    SpringBootTest
    -0.48
     uſed
    -0.47
     ſtill
    -0.47
    POSITIVE LOGITS
     purposes
    0.86
     sake
    0.66
    purposes
    0.56
     Purposes
    0.47
     Zwecke
    0.47
    来说
    0.45
    ForType
    0.43
     purpose
    0.43
    來說
    0.40
     reasons
    0.39
    Activations Density 0.528%

    No Known Activations