© 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. 16-GEMMASCOPE-RES-16K
    11. 7024
    Prev
    Next
    INDEX
    Explanations

    financial terms related to significant capital-raising activities

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

    "IPO", "issue", "sale", or "offering"

    np_acts-logits-general · gemini-2.0-flash

    public stock offering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     y
    -0.47
    Annotated
    -0.45
     pair
    -0.44
    oursquare
    -0.43
     radio
    -0.42
     driver
    -0.42
    ciless
    -0.41
     d
    -0.41
     te
    -0.40
     gott
    -0.40
    POSITIVE LOGITS
     raiſ
    1.03
     myſelf
    0.98
     itſelf
    0.88
     photolibrary
    0.83
     تانيه
    0.83
    ſelf
    0.83
     themſelves
    0.82
     uſed
    0.82
     poffible
    0.82
     AssemblyVersion
    0.81
    Activations Density 0.118%

    No Known Activations