© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 9380
    Prev
    Next
    INDEX
    Explanations

    characteristics of products in good condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.73
    :+:
    -0.67
    AndEndTag
    -0.65
    KURZBESCHREIBUNG
    -0.63
    GEBURTS
    -0.60
     hObject
    -0.59
    ClientSize
    -0.59
    ValueGeneration
    -0.55
    principalTable
    -0.53
    CloseOperation
    -0.53
    POSITIVE LOGITS
     Price
    0.58
     Willing
    0.55
     Estou
    0.53
     negotiable
    0.53
     состояние
    0.52
     Immaculate
    0.52
    USED
    0.52
    Istorija
    0.51
    Price
    0.51
     Bargaining
    0.51
    Activations Density 0.077%

    No Known Activations