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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 16108
    Prev
    Next
    INDEX
    Explanations

    terms associated with nutritional deficiencies and their impact on health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.52
     CreateTagHelper
    -0.52
    styleType
    -0.50
     الدولى
    -0.49
    saraba
    -0.46
     typelib
    -0.46
    Derbyniad
    -0.45
    WriteTagHelper
    -0.45
    BarStyle
    -0.44
    GOTREF
    -0.43
    POSITIVE LOGITS
     achievements
    0.77
     successes
    0.76
     logros
    0.73
     progress
    0.72
     accomplishments
    0.68
     success
    0.67
     Erfolge
    0.63
    complishments
    0.62
     prestasi
    0.60
    progress
    0.59
    Activations Density 0.366%

    No Known Activations