© 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. 8-GEMMASCOPE-RES-16K
    6. 15539
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and optimization, especially involving vectorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.75
    Ligações
    -0.69
    PasswordEncoder
    -0.66
    awaiter
    -0.60
    routeProvider
    -0.57
    esModule
    -0.56
    AutoScale
    -0.56
    campal
    -0.56
    ngdoc
    -0.55
     nargin
    -0.55
    POSITIVE LOGITS
     performance
    0.55
     efficiency
    0.53
    hdys
    0.52
    blockList
    0.52
    performance
    0.51
    InputBorder
    0.50
    usermodel
    0.50
     Efficiency
    0.49
    갓
    0.49
     كومونز
    0.48
    Activations Density 0.785%

    No Known Activations