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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117345
    Prev
    Next
    INDEX
    Explanations

    financial compensation and professional relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     enfans
    -0.44
     mør
    -0.43
     ķ
    -0.42
     besluit
    -0.42
     veřej
    -0.42
     preocupado
    -0.42
    nologies
    -0.41
    ColumnHeaders
    -0.41
     mennes
    -0.41
     waard
    -0.41
    POSITIVE LOGITS
    EndContext
    0.58
    AndEndTag
    0.50
     تانيه
    0.47
    новниш
    0.43
    Slf
    0.42
     anf
    0.41
    igshid
    0.41
    })*/
    0.40
    Datuak
    0.40
    PropertyChanging
    0.40
    Activations Density 0.244%

    No Known Activations