© 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. 8012
    Prev
    Next
    INDEX
    Explanations

    references to mathematical models or methodologies in research

    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
     AssemblyCompany
    -1.06
    __(/*!
    -0.96
     '\\;'
    -0.82
    (!__
    -0.79
     intStringLen
    -0.75
     Normdatei
    -0.75
     kaynağından
    -0.75
    tableFuture
    -0.74
    ⓘ
    -0.74
     onCreateView
    -0.72
    POSITIVE LOGITS
     getM
    1.02
     Madness
    1.02
     Mayhem
    0.88
     Mow
    0.79
     Mors
    0.78
     MMM
    0.77
     Mover
    0.77
     MCS
    0.75
     Münch
    0.74
     Morg
    0.73
    Activations Density 2.844%

    No Known Activations