Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8675
    Prev
    Next
    INDEX
    Explanations

    terminology related to physics and geometry, particularly focusing on arc shapes and physical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    djangoproject
    -0.50
    rmtree
    -0.44
     sàng
    -0.40
     Darm
    -0.39
    osexual
    -0.38
    AddTagHelper
    -0.37
     FirebaseAuth
    -0.36
    tonode
    -0.36
    gameserver
    -0.36
     desal
    -0.36
    POSITIVE LOGITS
     meme
    0.60
     arc
    0.60
     abs
    0.60
    arc
    0.59
     Arc
    0.58
     ARC
    0.58
     entropy
    0.57
    rum
    0.55
     mint
    0.55
     hum
    0.54
    Activations Density 0.397%

    No Known Activations