© 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. 3311
    Prev
    Next
    INDEX
    Explanations

    details about digital content access, protection, and features related to software or online services

    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
     uyar
    -0.50
    uleiro
    -0.48
    Tunisia
    -0.46
     laaj
    -0.45
    monton
    -0.44
    aziland
    -0.43
    toISOString
    -0.42
    (""));
    -0.41
    detectChanges
    -0.41
    rupulous
    -0.40
    POSITIVE LOGITS
     inaccessible
    1.09
     inacces
    0.99
     elusive
    0.81
     locked
    0.78
     Locked
    0.77
     unat
    0.76
    شهاد
    0.74
     unavailable
    0.74
     hidden
    0.72
     unreachable
    0.70
    Activations Density 0.401%

    No Known Activations