© 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. 1264
    Prev
    Next
    INDEX
    Explanations

    terms related to technical processes and frameworks in scientific and computing contexts

    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
    nocześnie
    -0.57
    ècie
    -0.52
     jusque
    -0.52
     Respectfully
    -0.52
     unexpectedly
    -0.51
    הערות
    -0.48
     borealis
    -0.48
    Linq
    -0.47
     hunch
    -0.47
     unwittingly
    -0.46
    POSITIVE LOGITS
     types
    1.69
     Types
    1.60
    Types
    1.46
    types
    1.39
     TYPES
    1.36
    TYPES
    1.34
     tipos
    1.22
     examples
    1.17
     Tipos
    1.14
     انواع
    1.14
    Activations Density 0.388%

    No Known Activations