© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4475
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to programming or software development

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

    proper names and geographic locations, particularly of people and places from Africa and other non-English speaking regions.

    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
    DockStyle
    -0.49
    aarrggbb
    -0.40
    UnsafeEnabled
    -0.40
    Manbalar
    -0.39
     hữu
    -0.37
    UpInside
    -0.37
    netinet
    -0.36
     Wesley
    -0.36
    stateProvider
    -0.35
    ChildScrollView
    -0.35
    POSITIVE LOGITS
     Ethiopian
    1.01
     Eritrea
    0.96
     Ethiopia
    0.95
    Ethio
    0.92
    Ethiopia
    0.90
     Ethio
    0.84
     Erit
    0.80
     Addis
    0.71
     Abyss
    0.63
     Tig
    0.59
    Activations Density 0.072%

    No Known Activations