© 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. 35-GEMMASCOPE-RES-16K
    11. 14338
    Prev
    Next
    INDEX
    Explanations

    references to racial or ethnic groups and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     people
    -0.61
     someone
    -0.56
     Zusammen
    -0.56
    someone
    -0.54
     mensen
    -0.54
    eseorang
    -0.53
     individuals
    -0.52
     somebody
    -0.51
    somebody
    -0.50
     alguém
    -0.49
    POSITIVE LOGITS
     whom
    0.74
    CloseOperation
    0.62
    whom
    0.60
    ंदीखरीदारी
    0.59
    WithIOException
    0.58
    featureID
    0.55
     faiths
    0.54
     wheelchairs
    0.54
    WEBPACK
    0.53
     незавершена
    0.53
    Activations Density 0.560%

    No Known Activations