© 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. 11103
    Prev
    Next
    INDEX
    Explanations

    instances of mergers or amalgamations involving organizations, places, or entities

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

    organizational combinations and structural changes involving entities joining together.

    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
    SOUNDBITE
    -0.33
    NewGuid
    -0.33
     circon
    -0.30
     Schall
    -0.28
    构
    -0.27
     bật
    -0.26
     depoz
    -0.26
    HasColumnType
    -0.26
     kick
    -0.26
    prepareStatement
    -0.26
    POSITIVE LOGITS
     merger
    2.39
     merge
    2.30
     merging
    2.27
     fusion
    2.22
     merged
    2.19
     merges
    2.09
     fusión
    2.03
     Merge
    1.92
     Merger
    1.89
    merge
    1.88
    Activations Density 0.589%

    No Known Activations