© 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. 21-GEMMASCOPE-RES-16K
    11. 7958
    Prev
    Next
    INDEX
    Explanations

    references to financial incentives or promotions related to products

    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
    kranz
    -0.47
     الرخصة
    -0.44
    rico
    -0.43
    Билгалдахарш
    -0.42
    发表于
    -0.40
    Dette
    -0.40
    OrUpdate
    -0.39
     fabricate
    -0.39
    interopRequire
    -0.39
    tso
    -0.38
    POSITIVE LOGITS
    Diweddarwch
    0.73
    ImageContext
    0.71
    JspWriter
    0.70
     ProtoMessage
    0.70
     المعيارى
    0.69
    SequentialGroup
    0.66
    Tikang
    0.66
    SBATCH
    0.65
    lujah
    0.64
    complexContent
    0.63
    Activations Density 0.070%

    No Known Activations