© 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. 12305
    Prev
    Next
    INDEX
    Explanations

    words associated with cleaning and maintenance processes

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

    words related to the removal of unwanted substances or buildup from surfaces.

    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
    StoryboardSegue
    -0.51
    تقاوى
    -0.49
     MediatR
    -0.45
    Географиясе
    -0.43
    OGND
    -0.43
    BeginContext
    -0.42
     estekak
    -0.41
     IndexPath
    -0.40
     فريبيس
    -0.39
    melons
    -0.39
    POSITIVE LOGITS
     dust
    1.32
     dirt
    1.22
     accumulation
    1.21
     accumulations
    1.12
     filth
    1.10
     accumulate
    1.09
    dirt
    1.09
     Accumulation
    1.08
    dust
    1.08
     accumulated
    1.08
    Activations Density 0.448%

    No Known Activations