© 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. 5011
    Prev
    Next
    INDEX
    Explanations

    instances of rebuilding or creating things from the beginning

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

    phrases describing building or creating something from the beginning without using existing materials.

    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
     continued
    -0.35
    Osob
    -0.35
    enumii
    -0.35
    onMouse
    -0.35
     membership
    -0.34
    Хьажоргаш
    -0.33
     Permanent
    -0.33
     Corral
    -0.32
     Mor
    -0.32
     textStatus
    -0.32
    POSITIVE LOGITS
     scratch
    1.40
     starting
    1.27
    Starting
    1.20
     afresh
    1.20
    starting
    1.20
     Starting
    1.13
    scratch
    1.13
     STARTING
    1.02
    Scratch
    1.02
     anew
    1.01
    Activations Density 0.421%

    No Known Activations