© 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. 3-GEMMASCOPE-RES-16K
    6. 15621
    Prev
    Next
    INDEX
    Explanations

    references to authors and their contributions in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.53
     Vertra
    -0.52
    bitField
    -0.49
    тарь
    -0.49
     nakalista
    -0.47
    횟
    -0.47
    ase
    -0.47
     Reverso
    -0.47
    enderror
    -0.45
     many
    -0.44
    POSITIVE LOGITS
    CloseOperation
    0.95
     متعلقه
    0.85
     itſelf
    0.76
    ſelf
    0.76
    AddTagHelper
    0.69
     devriez
    0.66
    ſelves
    0.66
    onBackPressed
    0.65
     yourselves
    0.65
    */;
    0.64
    Activations Density 0.590%

    No Known Activations