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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 431
    Prev
    Next
    INDEX
    Explanations

    phrases related to accounting services and opportunities

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

    financial and business service terms, pricing information, and transactional details.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodedInputStream
    -0.48
    XmlRootElement
    -0.48
    ckså
    -0.47
     zijne
    -0.46
    SupportActionBar
    -0.45
     JpaRepository
    -0.44
     виправивши
    -0.43
     weiss
    -0.42
    RemoveField
    -0.42
    Autoritní
    -0.41
    POSITIVE LOGITS
     solicitors
    0.65
     £
    0.62
     Solicitors
    0.59
     (£
    0.58
    はじめに
    0.57
    £
    0.57
     VAT
    0.56
     Solicitor
    0.56
     solicitor
    0.56
     postcode
    0.55
    Activations Density 0.474%

    No Known Activations