© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 7885
    Prev
    Next
    INDEX
    Explanations

    concepts related to exploration and discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    discovery and transformation

    np_acts-logits-general · gemini-2.0-flash

    exploration and discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    所
    -0.69
    MethodManager
    -0.65
      
    -0.64
    MatButtonModule
    -0.63
    genstein
    -0.59
    COHOL
    -0.58
    日在
    -0.57
    celotti
    -0.57
    法
    -0.56
    args
    -0.56
    POSITIVE LOGITS
     Theſe
    0.89
     Purdy
    0.80
    ,$_
    0.77
     découvrir
    0.77
     becauſe
    0.77
    ."</
    0.76
    theless
    0.75
     discovery
    0.74
    BibitemShut
    0.72
    例句
    0.71
    Activations Density 0.202%

    No Known Activations