© 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. 15-GEMMASCOPE-RES-16K
    11. 3366
    Prev
    Next
    INDEX
    Explanations

    phrases related to summarization and giving specific examples

    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
     intptr
    -0.92
    InjectAttribute
    -0.88
    ]--;
    -0.85
    Portail
    -0.83
     صوتيه
    -0.82
    期刊论文
    -0.80
    tagHelperRunner
    -0.77
     للاسماء
    -0.73
     betweenstory
    -0.73
     beginnetje
    -0.73
    POSITIVE LOGITS
     voici
    0.69
     folgendes
    0.67
    :
    0.62
     следующим
    0.55
     følgende
    0.55
     följande
    0.54
     şöyle
    0.53
     следующее
    0.52
    是这样的
    0.52
    Heres
    0.51
    Activations Density 0.374%

    No Known Activations