© 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. 13011
    Prev
    Next
    INDEX
    Explanations

    key points related to spatial descriptions and structures

    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
     AssemblyCompany
    -0.85
    featureID
    -0.77
    sizeCache
    -0.77
    principalColumn
    -0.77
    didn
    -0.71
    #+#
    -0.69
     Exactos
    -0.69
    StructEnd
    -0.66
    Didn
    -0.66
    NOPQRST
    -0.66
    POSITIVE LOGITS
     are
    1.68
     were
    1.16
     is
    1.15
     lies
    1.01
    are
    1.00
     estão
    0.99
    的是
    0.89
     Are
    0.86
     ARE
    0.85
     jsou
    0.84
    Activations Density 0.275%

    No Known Activations