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

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 12099
    Prev
    Next
    INDEX
    Explanations

    sections of text that indicate ongoing actions and prompts to continue reading

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

    Text after ellipses or continuation markers

    np_acts-logits-general · gemini-2.0-flash

    continue reading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ej
    -0.36
    rodek
    -0.35
    出た
    -0.34
    nale
    -0.33
     encar
    -0.32
    lange
    -0.31
    entrale
    -0.31
    lagem
    -0.31
    ticularly
    -0.31
    osis
    -0.31
    POSITIVE LOGITS
    httphttps
    0.84
     ProtoMessage
    0.69
    queryInterface
    0.68
    /*
    0.65
    rungsseite
    0.63
    /**
    0.63
     FetchType
    0.62
     surla
    0.61
     Италијани
    0.61
    mybatisplus
    0.59
    Activations Density 0.249%

    No Known Activations