© 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. 6242
    Prev
    Next
    INDEX
    Explanations

    references to press conferences and public statements by politicians

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

    preceding "conference" or related to "press"

    np_acts-logits-general · gemini-2.0-flash

    press conference and news

    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
     EconPapers
    -0.55
     незавершена
    -0.53
    Tracce
    -0.52
    FormTagHelper
    -0.52
     onPage
    -0.50
    úgó
    -0.49
    +#+#
    -0.49
    AccessorTable
    -0.49
    Sut
    -0.49
     föres
    -0.49
    POSITIVE LOGITS
     press
    1.49
     Press
    1.21
     reporters
    1.14
    press
    1.14
    Press
    1.13
     presse
    1.07
     PRESS
    1.04
     Presse
    1.01
     briefing
    0.99
     Reporters
    0.92
    Activations Density 0.113%

    No Known Activations