© 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. 14604
    Prev
    Next
    INDEX
    Explanations

    references to information technology roles and systems

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

    words and phrases related to information technology (IT) and technical infrastructure.

    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
     HasFactory
    -0.47
    krim
    -0.30
    ніципалі
    -0.28
    таратура
    -0.28
    BuildContext
    -0.27
     Prüf
    -0.26
     masculinos
    -0.26
    ervlak
    -0.26
     reproducción
    -0.24
    صاص
    -0.24
    POSITIVE LOGITS
     computer
    1.70
     Computer
    1.68
    computer
    1.64
    Computer
    1.60
     Computers
    1.54
     computers
    1.52
     IT
    1.48
    Computers
    1.46
     COMPUTER
    1.46
     ICT
    1.46
    Activations Density 0.542%

    No Known Activations