© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 5406
    Prev
    Next
    INDEX
    Explanations

    topics related to the significance of research and attention given to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.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
    WriteTagHelper
    -0.91
    AndEndTag
    -0.91
    ⓧ
    -0.85
    SequentialGroup
    -0.85
    fjspx
    -0.84
    IsContent
    -0.77
     дописавши
    -0.76
     Taktlose
    -0.74
    BeginContext
    -0.72
    GEBURTSDATUM
    -0.72
    POSITIVE LOGITS
     amount
    1.39
     much
    1.34
     lots
    1.32
     plenty
    1.26
     considerable
    1.16
    amount
    1.14
     mucho
    1.11
     Amount
    1.10
    Lots
    1.09
     Lots
    1.08
    Activations Density 0.566%

    No Known Activations