© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 12736
    Prev
    Next
    INDEX
    Explanations

    references to supplementary materials and articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ığ
    -0.48
     studies
    -0.47
    uu
    -0.46
     thường
    -0.46
     often
    -0.43
     spesso
    -0.43
    ...
    -0.42
    estu
    -0.41
     start
    -0.40
     السلام
    -0.40
    POSITIVE LOGITS
     kasarigan
    1.21
     >=",
    0.86
    клопе
    0.84
     nakalista
    0.84
    DockStyle
    0.80
     gynhyrchwyd
    0.80
     FontWeight
    0.79
    ]--;
    0.79
    IsContent
    0.79
     postIndex
    0.77
    Activations Density 0.649%

    No Known Activations