© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7068
    Prev
    Next
    INDEX
    Explanations

    terms related to financial reporting and quarter-based metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -0.91
     Theſe
    -0.88
     Reſ
    -0.87
     Cister
    -0.85
     Athenians
    -0.83
     Houſe
    -0.83
     مشين
    -0.81
    ſelves
    -0.80
    ſelf
    -0.80
     Diſ
    -0.79
    POSITIVE LOGITS
     assisted
    0.72
     III
    0.64
    SourceChecksum
    0.63
     guided
    0.62
    quarter
    0.62
     Quarter
    0.61
     Assist
    0.60
     II
    0.59
     assisting
    0.59
     Guided
    0.59
    Activations Density 0.138%

    No Known Activations