© 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. 2-GEMMASCOPE-RES-16K
    6. 5735
    Prev
    Next
    INDEX
    Explanations

    conditions related to the need for actions to be taken or requirements that must be met

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "},
    
    -0.66
    testens
    -0.64
     PagesJaunes
    -0.62
    niająca
    -0.62
    "]);
    
    -0.61
    ")){
    
    -0.61
    rrggbb
    -0.60
    ).]
    -0.59
    "]];
    -0.58
    BufferException
    -0.58
    POSITIVE LOGITS
    ContentAsync
    0.57
    JsonProperty
    0.55
    docx
    0.54
    ρους
    0.50
     prosím
    0.49
     sociali
    0.49
    șit
    0.48
    ObjectContext
    0.48
     anzi
    0.48
    قلال
    0.48
    Activations Density 0.269%

    No Known Activations