© 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. 18-GEMMASCOPE-RES-16K
    11. 1851
    Prev
    Next
    INDEX
    Explanations

    references to economic data and forecasts related to financial performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "[Year] was/is" or "[Year] will be"

    np_acts-logits-general · gemini-2.0-flash

    years described by 'to be' verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.89
    urrent
    -0.73
    DAILY
    -0.72
     tonight
    -0.71
     today
    -0.71
     ieri
    -0.69
    EndInit
    -0.68
     daily
    -0.67
    daily
    -0.66
     tomorrow
    -0.66
    POSITIVE LOGITS
     eventful
    0.73
     geprägt
    0.69
     characterized
    0.64
     marked
    0.63
     characterised
    0.57
     aikana
    0.57
    encodeWith
    0.56
     consacré
    0.56
     marqu
    0.56
     plagued
    0.54
    Activations Density 0.190%

    No Known Activations