© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8579
    Prev
    Next
    INDEX
    Explanations

    various types of metadata and formatting symbols used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.39
    ();?>
    -0.27
    
    -0.26
     the
    -0.26
     schlechter
    -0.25
     him
    -0.24
     behind
    -0.23
     towards
    -0.23
    <td>
    -0.23
     had
    -0.22
    POSITIVE LOGITS
     Wikimedijinoj
    0.75
     kasarigan
    0.70
     MainAxisSize
    0.69
     gynhyrchwyd
    0.67
    المشاركات
    0.66
     nakalista
    0.65
    WriteTagHelper
    0.62
     незавершена
    0.61
    Vidite
    0.61
    ſammen
    0.60
    Activations Density 0.795%

    No Known Activations