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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 14716
    Prev
    Next
    INDEX
    Explanations

    terms related to surfaces and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.46
    saraba
    -0.40
     <<<<<<<<<<<<<<
    -0.38
     اعت
    -0.35
     kehamilan
    -0.34
     krę
    -0.33
    imgdir
    -0.32
    PROLOG
    -0.32
    HasForeignKey
    -0.32
     EconPapers
    -0.32
    POSITIVE LOGITS
     surface
    4.00
    surface
    3.44
     Surface
    3.42
     SURFACE
    3.28
    Surface
    3.28
     surfaces
    3.03
    SURFACE
    2.91
     superficie
    2.75
     superfície
    2.72
     Surfaces
    2.59
    Activations Density 1.210%

    No Known Activations