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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15629
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings or sentiments

    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
    
    -0.64
    おお
    -0.60
     CreateTagHelper
    -0.55
    pius
    -0.49
     DialogInterface
    -0.48
    legungen
    -0.48
     jadx
    -0.48
    ाली
    -0.47
     Blas
    -0.47
     JADX
    -0.46
    POSITIVE LOGITS
     simply
    2.06
     simplemente
    1.91
    simply
    1.83
     semplicemente
    1.79
     just
    1.76
     simplesmente
    1.64
     simplement
    1.64
     просто
    1.59
     Simplemente
    1.57
     einfach
    1.56
    Activations Density 0.244%

    No Known Activations