© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15173
    Prev
    Next
    INDEX
    Explanations

    challenges and obstacles that hinder processes or progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    obstacles, impediments, or things that stand in the way of progress or goals.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.40
    adpleegd
    -0.39
     AppCompat
    -0.39
    WebServlet
    -0.39
    CopyWith
    -0.38
    prilis
    -0.38
    rosz
    -0.38
    rungsseite
    -0.37
    SuppressLint
    -0.36
     ujednoznacz
    -0.36
    POSITIVE LOGITS
     obstacles
    2.36
     barriers
    2.23
     obstacle
    2.22
     barrier
    2.08
    obstacles
    1.94
     hurdles
    1.94
     Barriers
    1.91
     impediments
    1.89
     obstáculos
    1.88
    obstacle
    1.87
    Activations Density 0.548%

    No Known Activations