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. 2065
    Prev
    Next
    INDEX
    Explanations

    metrics related to economic indicators and financial forecasts

    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
     المعيارى
    -0.74
     estekak
    -0.63
    RegistryLite
    -0.55
     ExecuteAsync
    -0.55
    الحياه
    -0.54
    podar
    -0.54
     ujednoznacz
    -0.53
    WriteTagHelper
    -0.53
     lenker
    -0.52
     насељу
    -0.51
    POSITIVE LOGITS
     rising
    1.41
     rises
    1.33
     rise
    1.33
     rose
    1.21
     risen
    1.19
    rising
    1.18
     climb
    1.15
     climbing
    1.13
     climbed
    1.13
     soared
    1.12
    Activations Density 0.798%

    No Known Activations