© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4544
    Prev
    Next
    INDEX
    Explanations

    keywords related to news and healthcare, particularly focusing on specialized content such as medical and sports news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.57
     ddelweddau
    -0.50
    arcoma
    -0.49
    antiate
    -0.48
    UseVisualStyle
    -0.48
     ModelAndView
    -0.46
    PostInfinity
    -0.45
    logna
    -0.44
    
    -0.44
     Manning
    -0.43
    POSITIVE LOGITS
    adget
    0.44
     MainAxisSize
    0.40
    $_['
    0.39
    AnimationsModule
    0.36
     drm
    0.34
     Landwir
    0.34
     TextAppearance
    0.33
    EndInit
    0.33
    seido
    0.32
    TagHelper
    0.32
    Activations Density 1.613%

    No Known Activations