© 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. 40-GEMMASCOPE-RES-16K
    11. 5583
    Prev
    Next
    INDEX
    Explanations

    mentions of political contests and decisions related to leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.51
    ptid
    -0.49
    脚注の使い方
    -0.46
    tiel
    -0.44
    ValueStyle
    -0.44
    onAttach
    -0.42
    MessageTagHelper
    -0.42
     виправивши
    -0.42
     Италијани
    -0.42
    UnusedPrivate
    -0.41
    POSITIVE LOGITS
     Malaysia
    0.96
     Malaysian
    0.95
    Malaysia
    0.86
     Malay
    0.83
     Kuala
    0.82
     Sarawak
    0.82
    Malay
    0.82
     Selangor
    0.81
     Johor
    0.75
     Penang
    0.73
    Activations Density 0.346%

    No Known Activations