© 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. 33-GEMMASCOPE-RES-16K
    11. 10875
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements and formatting commands in a coding or mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     If
    -0.41
    The
    -0.39
    において
    -0.39
    <b>
    -0.39
     AspNetCore
    -0.38
    ​
    -0.37
     
    -0.37
    ↵↵
    -0.35
    gebir
    -0.35
    If
    -0.35
    POSITIVE LOGITS
    IUrlHelper
    0.69
     Roskov
    0.66
     desmotivaciones
    0.65
    ArrowToggle
    0.64
    MessageTagHelper
    0.62
     Normdatei
    0.60
    OGND
    0.58
     Infór
    0.57
    genodigd
    0.57
     jScrollPane
    0.55
    Activations Density 6.552%

    No Known Activations