Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2154
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement or support in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    شهاد
    -0.74
     مشين
    -0.74
    jspb
    -0.72
     المعيارى
    -0.70
    yntaxException
    -0.68
    TagMode
    -0.67
     nakalista
    -0.67
     архивлан
    -0.66
    lorette
    -0.65
     Référence
    -0.64
    POSITIVE LOGITS
     plenamente
    0.71
     sentiments
    0.65
     wholeheartedly
    0.62
     parcialmente
    0.61
     penilaian
    0.60
     insofar
    0.58
     kebanyakan
    0.57
     assertion
    0.57
     notion
    0.57
     sentiment
    0.56
    Activations Density 0.334%

    No Known Activations