© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 4901
    Prev
    Next
    INDEX
    Explanations

    references to global locations and movements

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

    references to global scope or worldwide reach.

    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
     AssemblyCulture
    -0.68
    msgTypes
    -0.59
    WithIOException
    -0.57
     global
    -0.56
     betweenstory
    -0.56
    ranslated
    -0.55
    contentLoaded
    -0.54
    Попис
    -0.52
     CreateTagHelper
    -0.50
    torio
    -0.49
    POSITIVE LOGITS
    范围内
    0.60
     inteiro
    0.57
     entier
    0.54
    WIDE
    0.53
    wide
    0.52
     hinweg
    0.49
     boyunca
    0.42
     भर
    0.41
    Wide
    0.41
     cities
    0.39
    Activations Density 0.291%

    No Known Activations