© 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. 3008
    Prev
    Next
    INDEX
    Explanations

    instances of the special characters used for marking the beginning of text segments or code blocks

    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
    
    -0.98
     propOrder
    -0.86
     raiſ
    -0.80
     itſelf
    -0.80
     wikipagina
    -0.74
     Huguen
    -0.73
     Houſe
    -0.70
     DKK
    -0.67
     nakalista
    -0.66
     houſe
    -0.65
    POSITIVE LOGITS
     the
    1.60
     THE
    1.45
     The
    1.44
    The
    1.36
    THE
    1.17
    rethe
    1.15
    enthe
    1.11
    sthe
    1.10
    ithe
    1.02
    the
    1.00
    Activations Density 0.074%

    No Known Activations